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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     폐
    -0.07
     الخاص
    -0.06
    .med
    -0.06
    肖
    -0.06
     digits
    -0.06
    勤
    -0.06
     urn
    -0.06
     مهر
    -0.06
     MASK
    -0.06
     simultaneous
    -0.06
    POSITIVE LOGITS
    arily
    0.08
    år
    0.07
    IA
    0.07
    jet
    0.07
    dez
    0.07
    ้าย
    0.06
     può
    0.06
     Helpful
    0.06
    pletely
    0.06
    sec
    0.06
    Act Density 0.001%

    No Known Activations