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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <strong>
    0.58
    Y
    0.57
    C
    0.57
    W
    0.57
    P
    0.56
    ur
    0.54
    {
    0.52
    U
    0.52
    D
    0.51
    K
    0.50
    POSITIVE LOGITS
     utilizamos
    0.55
    ፨
    0.54
     rotacao
    0.54
     زیرمه
    0.52
     ګرځ
    0.51
     použití
    0.51
     utilizz
    0.50
     stockno
    0.50
     utiliz
    0.50
     څه
    0.50
    Act Density 0.001%

    No Known Activations