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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that address the reader directly

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

    you decide, want, need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.46
    Personendaten
    -0.46
    titleMargin
    -0.45
    afficheront
    -0.45
    WebVitals
    -0.43
     препратки
    -0.43
    ScopeManager
    -0.42
     мәкалә
    -0.39
     <=",
    -0.39
    WithMany
    -0.38
    POSITIVE LOGITS
     للاسماء
    0.52
    ⤹
    0.47
    sandalia
    0.46
     defire
    0.45
    :✨
    0.44
     Bump
    0.44
    __(/*!
    0.43
     bumped
    0.42
     getItemId
    0.42
     Dakota
    0.42
    Act Density 0.029%

    No Known Activations