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

    Neuronpedia

    INDEX
    Explanations

    instances of code blocks or preformatted text sections in the document

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

    pre followed byceq or user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    munition
    -0.55
     FetchType
    -0.51
    addComponent
    -0.50
    ipients
    -0.48
    ullah
    -0.48
     Penalty
    -0.48
    uggets
    -0.47
    pecabe
    -0.47
    amaño
    -0.47
    Pedagog
    -0.47
    POSITIVE LOGITS
    pre
    2.56
     pre
    1.80
    PRE
    1.56
    Pre
    1.50
     Pre
    1.38
     PRE
    1.30
     pré
    1.30
    pré
    1.23
    预
    1.03
    пре
    0.96
    Act Density 0.004%

    No Known Activations