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

    Neuronpedia

    INDEX
    Explanations

    ruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΑΛ
    -0.06
    ForeColor
    -0.06
     Nolan
    -0.06
    ctica
    -0.06
    辅
    -0.06
    测
    -0.06
    ีฬา
    -0.06
     永
    -0.05
     broken
    -0.05
    들과
    -0.05
    POSITIVE LOGITS
    [idx
    0.08
    Outside
    0.07
    .loc
    0.07
     indiscrim
    0.07
    .bool
    0.06
    .DO
    0.06
    ,std
    0.06
     sql
    0.06
     Selection
    0.06
    .custom
    0.06
    Act Density 0.051%

    No Known Activations