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

    Neuronpedia

    INDEX
    Explanations

    Otherwise, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *
    0.60
    <
    0.60
    u
    0.56
    F
    0.55
    W
    0.55
    +
    0.55
    I
    0.53
    [
    0.53
    ì
    0.53
    A
    0.53
    POSITIVE LOGITS
    CollectedField
    0.59
    ণিক
    0.55
     பத்து
    0.55
    হত
    0.54
    PatientR
    0.54
    TimeDict
    0.53
    ्राफी
    0.52
    DeviceCompliance
    0.52
     tụ
    0.52
    ंजय
    0.52
    Act Density 0.001%

    No Known Activations