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

    Neuronpedia

    INDEX
    Explanations

    Python errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subj
    -0.08
    _cg
    -0.07
    kání
    -0.07
     weekday
    -0.07
    )에
    -0.07
     arşiv
    -0.06
     covariance
    -0.06
    alim
    -0.06
     Newcastle
    -0.06
    ह
    -0.06
    POSITIVE LOGITS
    _passed
    0.06
     StyleSheet
    0.06
    content
    0.06
     %↵
    0.06
     最
    0.06
     кух
    0.06
     Tau
    0.06
     вам
    0.05
    sass
    0.05
    .Merge
    0.05
    Act Density 0.004%

    No Known Activations