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

    Neuronpedia

    INDEX
    Explanations

    dees nuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thích
    1.13
    ем
    1.10
     for
    0.96
     сдела
    0.96
    ാൻഡ്
    0.96
    твори
    0.95
    செய்ய
    0.95
    ер
    0.94
     puedas
    0.91
     m
    0.91
    POSITIVE LOGITS
    1
    1.29
    ł
    1.17
    ك
    1.16
    wang
    1.15
    ur
    1.13
    be
    1.13
    ide
    1.09
    ?
    1.08
    ha
    1.05
    !
    1.04
    Act Density 0.000%

    No Known Activations