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

    Neuronpedia

    INDEX
    Explanations

    code imports and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     고급
    0.48
    Ⴊ
    0.47
     plików
    0.44
    Գ
    0.44
    夗
    0.43
    Graph
    0.43
     kro
    0.42
     উত্তম
    0.42
     வடிவமை
    0.42
     آسان
    0.41
    POSITIVE LOGITS
     imports
    0.39
    import
    0.38
     Imports
    0.37
     import
    0.37
     imbalances
    0.35
     nub
    0.35
     aparent
    0.35
    நாதன்
    0.35
    #![
    0.35
     imbalance
    0.34
    Act Density 0.312%

    No Known Activations