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

    Neuronpedia

    INDEX
    Explanations

    .js, .json, .cpp, .h, .module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    íticos
    0.53
     canaux
    0.49
    鍒
    0.48
    的是
    0.47
    지는
    0.47
    상은
    0.46
     डालें
    0.45
    ЕМ
    0.44
     LEAD
    0.44
     PRODUCTS
    0.44
    POSITIVE LOGITS
     অথবা
    0.48
    s
    0.46
    alin
    0.44
    または
    0.44
     principal
    0.42
     or
    0.41
    andal
    0.40
     oder
    0.39
     ಅಥವಾ
    0.39
     или
    0.39
    Act Density 0.010%

    No Known Activations