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

    Neuronpedia

    INDEX
    Explanations

    references to specific cultural, regional, or institutional identities

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

    names of places and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.59
     aDecoder
    -0.52
     Offisielt
    -0.51
    StoreMessageInfo
    -0.50
     pensaba
    -0.49
    ugges
    -0.48
     prejudiced
    -0.48
     lectured
    -0.47
    Serviço
    -0.46
     recommandée
    -0.46
    POSITIVE LOGITS
     resourceCulture
    0.44
    енча
    0.32
     talent
    0.30
    коменду
    0.29
    ReusableCell
    0.29
     ent
    0.29
    withIdentifier
    0.28
     tur
    0.28
     Means
    0.28
    Means
    0.28
    Act Density 0.013%

    No Known Activations