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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    扫码
    -0.07
     Hide
    -0.07
     الم
    -0.06
    ưỡng
    -0.06
     bombing
    -0.06
    前方
    -0.06
     Icons
    -0.06
     "),↵
    -0.06
    closing
    -0.06
     tangent
    -0.06
    POSITIVE LOGITS
     일이
    0.08
    ◁
    0.07
     выпус
    0.07
    ีย
    0.07
    _targets
    0.07
     Within
    0.07
     Na
    0.07
    .sup
    0.07
    Many
    0.07
    .Simple
    0.07
    Act Density 0.001%

    No Known Activations