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

    Neuronpedia

    INDEX
    Explanations

    Code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zburg
    -0.09
     chimney
    -0.07
     aim
    -0.07
    ycz
    -0.07
    _Get
    -0.07
    .zip
    -0.07
     Rio
    -0.07
    yı
    -0.06
     cref
    -0.06
     Commissioners
    -0.06
    POSITIVE LOGITS
     predicts
    0.08
    🔫
    0.07
    decoded
    0.07
     miejscowości
    0.07
    💩
    0.07
     parses
    0.07
     unordered
    0.07
    饱和
    0.06
     unrelated
    0.06
     CASE
    0.06
    Act Density 0.036%

    No Known Activations