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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tops
    -0.07
     с
    -0.07
     marine
    -0.07
    _retry
    -0.07
     ill
    -0.06
    termination
    -0.06
    置
    -0.06
    -la
    -0.06
    Friday
    -0.06
    .split
    -0.06
    POSITIVE LOGITS
    _signal
    0.07
     tutte
    0.07
     alınması
    0.06
    assis
    0.06
    ramework
    0.06
    播放
    0.06
    ハイ
    0.06
     velik
    0.06
     Apost
    0.06
     getSession
    0.06
    Act Density 0.002%

    No Known Activations