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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENABLE
    -0.06
     biz
    -0.06
     cứ
    -0.06
    間に
    -0.06
     běž
    -0.06
    Td
    -0.06
     �
    -0.06
     борь
    -0.06
    赞
    -0.06
     offsetX
    -0.06
    POSITIVE LOGITS
    [group
    0.07
    。“
    0.07
     conventions
    0.07
    ！↵↵
    0.06
     svm
    0.06
    ）。↵↵
    0.06
    multi
    0.06
    ////////////////////////////////////////////////////////////////////////////
    0.06
     translator
    0.06
    useum
    0.06
    Act Density 0.131%

    No Known Activations