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

    Neuronpedia

    INDEX
    Explanations

    data extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erm
    -0.07
    .perform
    -0.06
    ימו
    -0.06
     vigorously
    -0.06
     Jewel
    -0.06
     juven
    -0.06
    уз
    -0.06
    贸
    -0.06
    chsel
    -0.06
    mother
    -0.06
    POSITIVE LOGITS
    ')}↵
    0.08
     Titanic
    0.07
    另一个
    0.07
     trays
    0.07
     ByVal
    0.07
    ,p
    0.07
     playlist
    0.07
     Validation
    0.07
    事关
    0.07
     PropTypes
    0.07
    Act Density 0.034%

    No Known Activations