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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NULL
    -0.07
    llll
    -0.06
     Unlimited
    -0.06
    elled
    -0.06
    _UNUSED
    -0.06
    翼
    -0.06
    _EXPRESSION
    -0.06
     limit
    -0.06
    ем
    -0.06
    ENAME
    -0.06
    POSITIVE LOGITS
    tk
    0.07
     상담
    0.07
     основе
    0.07
    ).^
    0.07
    抓
    0.06
    _sex
    0.06
     Ph
    0.06
    430
    0.06
     PSP
    0.06
    км
    0.06
    Act Density 0.008%

    No Known Activations