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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่ง
    -0.07
    λος
    -0.07
     oyun
    -0.07
    courses
    -0.06
     Kanunu
    -0.06
     Bros
    -0.06
    시간
    -0.06
    adays
    -0.06
     ninh
    -0.06
    translator
    -0.06
    POSITIVE LOGITS
     SCIP
    0.07
    -condition
    0.07
    _util
    0.07
     salv
    0.06
    .factor
    0.06
    .defer
    0.06
     gear
    0.06
    (tile
    0.06
    _escape
    0.06
     mocking
    0.06
    Act Density 0.006%

    No Known Activations