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

    Neuronpedia

    INDEX
    Explanations

    language or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     painfully
    0.36
     samot
    0.34
     ਅਤੇ
    0.33
     von
    0.33
     ไอ้
    0.33
     observed
    0.32
    そして
    0.31
     және
    0.31
     monstrous
    0.31
    zeichnis
    0.30
    POSITIVE LOGITS
     или
    0.73
     અથવા
    0.68
    或其他
    0.68
     hoặc
    0.66
     அல்லது
    0.65
     లేదా
    0.65
    或
    0.65
     أو
    0.64
     또는
    0.63
     veya
    0.61
    Act Density 3.962%

    No Known Activations