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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stringBuffer
    -0.08
    此文
    -0.07
    ㎏
    -0.07
    花朵
    -0.07
    executor
    -0.07
    -element
    -0.07
    례
    -0.07
     Magnum
    -0.07
    (outfile
    -0.07
    'er
    -0.06
    POSITIVE LOGITS
    NegativeButton
    0.07
    _pat
    0.07
    敢于
    0.07
    𬤊
    0.07
    ologists
    0.06
    gregator
    0.06
     employer
    0.06
    诽
    0.06
    婤
    0.06
    꼰
    0.06
    Act Density 0.020%

    No Known Activations