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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CALL
    -0.07
    _SB
    -0.07
     Sele
    -0.06
     REFER
    -0.06
     mắt
    -0.06
     цю
    -0.06
     ROW
    -0.06
    rok
    -0.06
    明
    -0.06
     discretionary
    -0.06
    POSITIVE LOGITS
    (parseInt
    0.07
    -winning
    0.06
     knows
    0.06
    ضي
    0.06
    058
    0.06
    isLoading
    0.06
    uset
    0.06
    arranty
    0.06
    checks
    0.06
    Delta
    0.06
    Act Density 0.002%

    No Known Activations