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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کلاس
    -0.06
    버전
    -0.06
    шила
    -0.06
    ecedor
    -0.06
     العق
    -0.06
     +'
    -0.06
    trim
    -0.06
    �
    -0.06
     신입
    -0.06
    ynos
    -0.06
    POSITIVE LOGITS
    _connections
    0.07
    (inst
    0.07
    ）↵↵
    0.06
    ector
    0.06
     "..
    0.06
    CellValue
    0.06
     TMPro
    0.06
    ’.↵↵
    0.06
    Selectable
    0.06
    véd
    0.06
    Act Density 0.006%

    No Known Activations