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

    Neuronpedia

    INDEX
    Explanations

    resistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.08
    iams
    1.06
    U
    0.99
    ი
    0.97
    ts
    0.96
    니다
    0.95
    tl
    0.93
    Frames
    0.93
    mil
    0.91
    s
    0.90
    POSITIVE LOGITS
     incrível
    1.42
    貽
    1.39
     navegador
    1.36
     parody
    1.34
     toprak
    1.33
     aqueles
    1.32
     burrito
    1.31
     semelhante
    1.29
     dezelfde
    1.28
     thắng
    1.27
    Act Density 0.009%

    No Known Activations