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

    Neuronpedia

    INDEX
    Explanations

    Assertiveness and limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     되는
    -0.06
     ashamed
    -0.06
    )NULL
    -0.06
    _batches
    -0.06
    _recall
    -0.06
    webElementX
    -0.06
     fst
    -0.06
     cif
    -0.06
    tensor
    -0.06
     通
    -0.06
    POSITIVE LOGITS
     San
    0.06
     نوفمبر
    0.06
    Sil
    0.06
     Kavanaugh
    0.06
    """↵↵↵
    0.06
    Florida
    0.06
    تف
    0.06
     مقایسه
    0.06
     phận
    0.06
    stup
    0.06
    Act Density 0.035%

    No Known Activations