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

    Neuronpedia

    INDEX
    Explanations

    annual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (guess
    -0.07
     سه
    -0.07
    _sta
    -0.06
    _BUSY
    -0.06
    /player
    -0.06
     '#'
    -0.06
    defines
    -0.06
     tes
    -0.06
    (codec
    -0.06
    ![
    -0.06
    POSITIVE LOGITS
     trục
    0.07
    اوت
    0.07
    rated
    0.06
     исключ
    0.06
    уванні
    0.06
     disposal
    0.06
    vat
    0.06
    cached
    0.06
    luğ
    0.06
    Got
    0.06
    Act Density 0.002%

    No Known Activations