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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.75
    клопе
    -0.73
     للاسماء
    -0.69
    InitVars
    -0.68
     виправивши
    -0.66
    पया
    -0.65
    ValueGenerated
    -0.63
    ihnachten
    -0.60
     culoare
    -0.60
     autorytatywna
    -0.60
    POSITIVE LOGITS
     performance
    0.56
     undoubtedly
    0.52
     Heller
    0.51
     undeniably
    0.50
     wel
    0.50
    olese
    0.49
    hlands
    0.49
    iolis
    0.49
     unquestionably
    0.49
    nar
    0.48
    Act Density 1.546%

    No Known Activations