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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     justification
    -0.06
    ブロ
    -0.06
    _RATIO
    -0.06
     código
    -0.06
     rq
    -0.06
     canon
    -0.06
    rawn
    -0.06
    undos
    -0.06
    notation
    -0.06
     Euler
    -0.06
    POSITIVE LOGITS
    CppI
    0.07
     노출등록
    0.07
    :SetPoint
    0.07
    AMILY
    0.06
     کمی
    0.06
    ='<
    0.06
    िब
    0.06
     Wilmington
    0.06
    вад
    0.06
    差
    0.06
    Act Density 0.058%

    No Known Activations