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

    Neuronpedia

    INDEX
    Explanations

    recipes and garnish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eps
    -0.08
     dear
    -0.07
    !")
↵
    -0.07
     sings
    -0.07
     Plays
    -0.07
    .support
    -0.07
     Fiction
    -0.07
    烟火
    -0.07
    enght
    -0.06
    话剧
    -0.06
    POSITIVE LOGITS
     Balance
    0.06
    ROI
    0.06
     skal
    0.06
     (%
    0.06
     QC
    0.06
    _decode
    0.06
     Brook
    0.06
    _GT
    0.06
     Carlo
    0.06
    oho
    0.06
    Act Density 0.030%

    No Known Activations