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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صہی
    0.90
    থন
    0.88
     शहद
    0.84
     الهم
    0.80
     мысли
    0.80
     Jerez
    0.80
     kwargs
    0.79
    婍
    0.79
    ﺛ
    0.78
     diethyl
    0.77
    POSITIVE LOGITS
    ça
    0.81
    कर
    0.76
    年
    0.73
    ze
    0.70
    4
    0.69
    ulle
    0.67
    氓
    0.67
    देव
    0.66
    MA
    0.65
    2
    0.65
    Act Density 0.001%

    No Known Activations