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

    Neuronpedia

    INDEX
    Explanations

    class inheritance definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.66
    In
    0.58
    ال
    0.53
    '
    0.51
    他
    0.50
    It
    0.49
    ing
    0.48
    On
    0.47
     In
    0.47
    ونها
    0.47
    POSITIVE LOGITS
    ጠቀም
    0.56
    谿
    0.53
    ንን
    0.51
     protracted
    0.50
    스키
    0.50
     sweating
    0.48
    قوم
    0.47
    ików
    0.47
    発達
    0.46
    뻗
    0.45
    Act Density 0.005%

    No Known Activations