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

    Neuronpedia

    INDEX
    Explanations

    references to specific moments and times in the narrative

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

    that moment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.52
    ņas
    -0.46
    LabelTagHelper
    -0.43
     Begleitung
    -0.43
     škoda
    -0.41
    참고
    -0.40
    /******/
    -0.40
    parsedMessage
    -0.39
     nahilalakip
    -0.38
    ąpi
    -0.37
    POSITIVE LOGITS
    setCharacter
    0.51
    principalColumn
    0.44
    quelize
    0.42
     naquele
    0.41
     Reverso
    0.40
    AuthContext
    0.39
     Exactos
    0.39
     referrerpolicy
    0.39
     мәкал
    0.39
    DEAN
    0.39
    Act Density 0.064%

    No Known Activations