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

    Neuronpedia

    INDEX
    Explanations

    sets of things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ryder
    -0.06
    �
    -0.06
     Bard
    -0.06
     Đảng
    -0.06
     ثابت
    -0.06
    ateg
    -0.06
    sten
    -0.06
     MSM
    -0.06
    iteleri
    -0.06
    CHIP
    -0.06
    POSITIVE LOGITS
    exclude
    0.07
     cuz
    0.06
    مع
    0.06
     Jahr
    0.06
    .sol
    0.06
    _loc
    0.06
    _zero
    0.06
     Sanct
    0.06
    /weather
    0.06
    months
    0.06
    Act Density 0.010%

    No Known Activations