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

    Neuronpedia

    INDEX
    Explanations

    import pandas as pd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᑦ
    0.81
    セプト
    0.81
    ARR
    0.79
    arr
    0.77
    SourceObject
    0.76
    ધ
    0.76
    empre
    0.73
    avaju
    0.70
    0.70
    スープ
    0.70
    POSITIVE LOGITS
     pd
    1.19
     PD
    1.08
     Pd
    1.05
    pd
    0.96
    PD
    0.95
     Pud
    0.94
     BD
    0.91
    Pd
    0.89
     पीडी
    0.80
     पांड
    0.79
    Act Density 0.006%

    No Known Activations