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

    Neuronpedia

    INDEX
    Explanations

    roman history and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.91
    0
    0.88
    5
    0.84
    4
    0.81
    r
    0.79
    3
    0.79
    *
    0.79
    8
    0.79
     (
    0.78
     +
    0.78
    POSITIVE LOGITS
     genealogical
    1.09
     MDET
    1.00
     notizie
    0.93
     poesía
    0.90
     personenbez
    0.89
     genealog
    0.88
     bitOp
    0.88
     collezione
    0.88
     poslov
    0.86
    GALAD
    0.86
    Act Density 0.000%

    No Known Activations