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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and interactions between characters

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

    speaking actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.66
    expandindo
    -0.53
     Autorizaciones
    -0.51
    astéroïdes
    -0.50
    tagHelperRunner
    -0.50
    adaptiveStyles
    -0.50
     iconLine
    -0.49
    getOutputStream
    -0.47
     estekak
    -0.47
    AutoField
    -0.47
    POSITIVE LOGITS
    ñola
    0.37
    Lähteet
    0.36
     sounding
    0.36
    blon
    0.36
    temp
    0.35
     lago
    0.35
    SWE
    0.35
     viſ
    0.35
     lese
    0.35
    toner
    0.34
    Act Density 0.009%

    No Known Activations