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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pdata
    -0.07
    tested
    -0.07
    ارات
    -0.07
     PDT
    -0.07
    등
    -0.07
    uyễn
    -0.06
     n
    -0.06
     путем
    -0.06
    .ToLower
    -0.06
    .fm
    -0.06
    POSITIVE LOGITS
    administrator
    0.06
    ence
    0.06
    .setStyleSheet
    0.06
    ileo
    0.06
    _over
    0.06
    Need
    0.06
    Additionally
    0.06
    ochen
    0.06
    vy
    0.06
    白
    0.06
    Act Density 0.001%

    No Known Activations