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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exual
    -0.07
    Bu
    -0.07
    _HIDDEN
    -0.07
    HashTable
    -0.07
    ئ
    -0.07
    -DD
    -0.07
    این
    -0.06
    Whether
    -0.06
     кра
    -0.06
    HX
    -0.06
    POSITIVE LOGITS
    ео
    0.06
    itz
    0.06
    趣
    0.06
    hPa
    0.06
     countdown
    0.06
    lay
    0.06
     مدينة
    0.06
    ,state
    0.05
    ']),
    0.05
     McA
    0.05
    Act Density 0.429%

    No Known Activations