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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _extent
    -0.07
    وار
    -0.07
     stealing
    -0.06
    YEAR
    -0.06
    lédl
    -0.06
    vi
    -0.06
     ct
    -0.06
     evapor
    -0.06
    搜
    -0.06
    scan
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ②
    0.07
    ..."↵
    0.07
    8
    0.07
    приєм
    0.06
     전체
    0.06
    9
    0.06
    istrovství
    0.06
     Deserialize
    0.06
    .)↵
    0.06
    Act Density 0.041%

    No Known Activations