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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and descriptions of individuals

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

    she makes her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.53
    QMetaType
    -0.53
     Roskov
    -0.50
    FieldBuilder
    -0.49
    digarh
    -0.48
    FromNib
    -0.47
     surla
    -0.45
     shipment
    -0.44
     mergeFrom
    -0.44
    cency
    -0.43
    POSITIVE LOGITS
    acirc
    0.43
     loved
    0.43
     always
    0.40
     dignité
    0.37
     charité
    0.36
     zawsze
    0.36
     auroit
    0.36
    onAttach
    0.35
     altijd
    0.35
    NgModule
    0.35
    Act Density 0.001%

    No Known Activations