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

    Neuronpedia

    INDEX
    Explanations

    Mrs. and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ienz
    0.76
    0.71
    endswith
    0.71
    pneum
    0.70
    flo
    0.69
     جي
    0.69
    ateau
    0.69
    ipt
    0.68
    0.68
    Dt
    0.68
    POSITIVE LOGITS
    intă
    0.87
    从
    0.78
     जड़ों
    0.78
    ają
    0.77
    초
    0.77
     további
    0.75
     Từ
    0.75
    मिथ
    0.75
     From
    0.74
    鐧
    0.74
    Act Density 0.001%

    No Known Activations