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

    Neuronpedia

    INDEX
    Explanations

    Joe Biden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    1.93
     jurídica
    1.89
    вать
    1.77
     alternately
    1.73
    fia
    1.70
     selves
    1.69
     exponencial
    1.66
     isomers
    1.63
    ными
    1.63
     ligados
    1.62
    POSITIVE LOGITS
    и
    2.08
    ної
    1.83
    น
    1.75
     dotycz
    1.73
    ﻱ
    1.73
    ość
    1.73
    able
    1.59
    ्
    1.59
    ل
    1.59
    ljen
    1.58
    Act Density 0.001%

    No Known Activations