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

    Neuronpedia

    INDEX
    Explanations

    words related to technical devices and specific geopolitical concerns

    oai_token-act-pair · gemini-2.0-flash

    safety and mechanics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.53
     Extragalactic
    -0.51
    URB
    -0.51
     pinulongan
    -0.50
    djangoproject
    -0.49
    ellery
    -0.49
    itorious
    -0.48
    styleType
    -0.48
    archiviato
    -0.48
     EPR
    -0.47
    POSITIVE LOGITS
    DoubleQuotes
    0.58
    Географи
    0.56
     branche
    0.54
    thâu
    0.53
    ágok
    0.52
    iastes
    0.52
     HasFactory
    0.52
    かというと
    0.51
    SequentialGroup
    0.50
     للمعارف
    0.50
    Act Density 2.070%

    No Known Activations