Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pronouns and modal verbs indicating agency or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Let followed by variable

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that begin a sentence — especially short, capitalized sentence-start words (e.g., "A", "I", "Let", "This").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     незавершена
    -0.77
    localctx
    -0.72
    WebElementEntity
    -0.71
     Италијани
    -0.67
     resourceCulture
    -0.65
    principalColumn
    -0.64
    Jîn
    -0.64
    Autoritní
    -0.63
    UrlResolution
    -0.62
     Administrativna
    -0.61
    POSITIVE LOGITS
     Stille
    0.38
     ponts
    0.37
    getMenuInflater
    0.36
     boks
    0.36
    inette
    0.36
    ieme
    0.35
     Krä
    0.35
     Swe
    0.34
     Mini
    0.34
    string
    0.34
    Act Density 0.108%

    No Known Activations