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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions or scheduling

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

    for further purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.40
    getMenuInflater
    -0.37
    ToProps
    -0.37
     Mund
    -0.37
    Mund
    -0.36
    HNO
    -0.35
    OfClass
    -0.35
    aleg
    -0.35
     QUE
    -0.35
     nonatomic
    -0.35
    POSITIVE LOGITS
     zostać
    0.67
     zostanie
    0.57
    ถูก
    0.56
     Wikiseite
    0.52
     zostało
    0.52
    ValueStyle
    0.52
    ScopeManager
    0.50
     zosta
    0.50
     trebui
    0.50
    expandindo
    0.49
    Act Density 0.123%

    No Known Activations