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

    Neuronpedia

    INDEX
    Explanations

    names of entities or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.70
    f
    0.68
    ed
    0.67
    ite
    0.59
    6
    0.59
    ir
    0.58
    सँग
    0.58
    ad
    0.57
    5
    0.57
    and
    0.56
    POSITIVE LOGITS
     to
    0.75
     that
    0.55
    нтов
    0.54
     пациен
    0.52
     bebe
    0.48
     it
    0.48
     관리
    0.47
     ого
    0.47
     ਕਿ
    0.45
     že
    0.45
    Act Density 0.319%

    No Known Activations