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

    Neuronpedia

    INDEX
    Explanations

    wage garnishments and refunds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intervene
    -0.08
     Dav
    -0.07
     Basis
    -0.07
     mrb
    -0.07
     Revolution
    -0.07
     Ens
    -0.06
     interracial
    -0.06
     quat
    -0.06
     NDEBUG
    -0.06
     avi
    -0.06
    POSITIVE LOGITS
    ."+
    0.07
    OTAL
    0.07
    AINED
    0.07
    面板
    0.06
    lobs
    0.06
    ذاكرة
    0.06
    🏍
    0.06
    toLowerCase
    0.06
     annoyance
    0.06
    _keywords
    0.06
    Act Density 0.023%

    No Known Activations