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

    Neuronpedia

    INDEX
    Explanations

    assertions and contradictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    احة
    -0.07
    ↵				↵
    -0.06
    /ac
    -0.06
    are
    -0.06
     schwar
    -0.06
    ARE
    -0.06
    [strlen
    -0.06
    [char
    -0.06
     isEqualToString
    -0.06
     scalp
    -0.06
    POSITIVE LOGITS
    �
    0.07
    닝
    0.07
    _CALLBACK
    0.06
     controlId
    0.06
    ्ठ
    0.06
    那么
    0.06
     StringType
    0.06
    으나
    0.06
    pring
    0.06
     turtle
    0.06
    Act Density 0.004%

    No Known Activations