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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alat
    -0.06
     opener
    -0.06
     Cook
    -0.06
    _bit
    -0.06
     xl
    -0.06
    Cook
    -0.06
    itting
    -0.06
     ratio
    -0.06
    ?=
    -0.06
    (cli
    -0.06
    POSITIVE LOGITS
     شناسی
    0.07
     piss
    0.07
    flu
    0.07
    _archive
    0.07
     won
    0.07
    蜘蛛词
    0.07
     خواه
    0.07
     Immutable
    0.06
    iêu
    0.06
     excuses
    0.06
    Act Density 0.148%

    No Known Activations