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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KT
    -0.07
    imators
    -0.07
     Zo
    -0.06
     فی
    -0.06
    licant
    -0.06
    .Selection
    -0.06
    др
    -0.06
     Constant
    -0.06
     empire
    -0.06
     dl
    -0.06
    POSITIVE LOGITS
    اا
    0.07
    负
    0.06
     bufsize
    0.06
    (pdev
    0.06
    [arr
    0.06
     distrib
    0.06
    /how
    0.06
    "};↵↵
    0.06
    _Reset
    0.06
    isodes
    0.06
    Act Density 0.000%

    No Known Activations