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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Legal
    -0.08
     Driving
    -0.08
    褕
    -0.07
    _Open
    -0.07
    하신
    -0.07
    fälle
    -0.07
    ORIZ
    -0.07
     directs
    -0.07
    $$$
    -0.06
    nam
    -0.06
    POSITIVE LOGITS
     Lantern
    0.08
    觉得自己
    0.08
     cherry
    0.07
    ％
    0.07
    Encoding
    0.07
    readcrumb
    0.07
     playoffs
    0.07
    瓢
    0.07
    _crop
    0.07
    まあ
    0.06
    Act Density 0.004%

    No Known Activations