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

    Neuronpedia

    INDEX
    Explanations

    events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tolik
    -0.06
     accelerated
    -0.06
    仮
    -0.06
    arten
    -0.06
     car
    -0.06
     curso
    -0.06
    sw
    -0.06
    044
    -0.06
    Gamma
    -0.06
    8
    -0.06
    POSITIVE LOGITS
    áno
    0.07
     引
    0.06
    .mail
    0.06
     pornost
    0.06
     Uint
    0.06
    \Domain
    0.06
    _tra
    0.06
    '].
    0.06
    zsche
    0.06
    렵
    0.06
    Act Density 0.091%

    No Known Activations