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

    Neuronpedia

    INDEX
    Explanations

    infer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    founded
    -0.85
     founded
    -0.83
    equipped
    -0.75
     HasFactory
    -0.73
    AnchorTagHelper
    -0.69
     equipped
    -0.68
     externi
    -0.66
     Италијани
    -0.63
     censiti
    -0.63
     fondé
    -0.59
    POSITIVE LOGITS
     تانيه
    0.64
    DebuggerNonUser
    0.63
     ModelExpression
    0.60
    ⓧ
    0.59
     Вікіпе
    0.58
     beginnetje
    0.55
    #
    0.54
     commonest
    0.54
    april
    0.52
    :]:
    0.49
    Act Density 0.371%

    No Known Activations