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

    Neuronpedia

    INDEX
    Explanations

    narrative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charms
    -0.07
     wrink
    -0.06
     плеч
    -0.06
     DAR
    -0.06
     anth
    -0.06
     Bonds
    -0.06
     COS
    -0.06
     предпоч
    -0.06
    ули
    -0.06
    OLS
    -0.06
    POSITIVE LOGITS
    _view
    0.07
    操作
    0.07
    Caller
    0.06
    Execute
    0.06
    _BE
    0.06
     Of
    0.06
    _union
    0.06
    inos
    0.06
    进行
    0.06
    ?,↵
    0.06
    Act Density 0.048%

    No Known Activations