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

    Neuronpedia

    INDEX
    Explanations

    grip fighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suspected
    0.77
     Susan
    0.75
     m
    0.72
    !
    0.72
     web
    0.70
     un
    0.70
     nonprofit
    0.70
     conco
    0.68
     lawsuit
    0.68
     spouse
    0.67
    POSITIVE LOGITS
     oWord
    1.04
    ómetro
    1.03
     वनडे
    1.01
     jogadores
    0.97
    óso
    0.96
    utebol
    0.95
     Entscheid
    0.94
     glTexParameteri
    0.93
    ेश्च
    0.92
    球员
    0.92
    Act Density 0.049%

    No Known Activations