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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    macro
    -0.08
     quis
    -0.08
    -informed
    -0.08
    mdir
    -0.08
     CSV
    -0.08
    -me
    -0.07
    ैय
    -0.07
    orzyst
    -0.07
    CSV
    -0.07
     kiş
    -0.07
    POSITIVE LOGITS
     perched
    0.09
     चम
    0.09
     reminiscent
    0.09
     रंग
    0.08
    闪
    0.08
     сотрудники
    0.08
     നിറ
    0.08
     glowing
    0.08
     રંગ
    0.08
     волос
    0.08
    Act Density 0.075%

    No Known Activations