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

    Neuronpedia

    INDEX
    Explanations

    brag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    눌
    -0.08
    诓
    -0.07
    _WIN
    -0.07
     contests
    -0.07
     alış
    -0.07
    诳
    -0.07
    ถน
    -0.06
     Explos
    -0.06
    itez
    -0.06
    疖
    -0.06
    POSITIVE LOGITS
     하
    0.07
    lical
    0.07
     Fil
    0.07
    並
    0.06
    Bah
    0.06
     Di
    0.06
    差不多
    0.06
     FR
    0.06
    .Back
    0.06
    sequ
    0.06
    Act Density 0.088%

    No Known Activations