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

    Neuronpedia

    INDEX
    Explanations

    units and segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Allora
    0.62
    সব
    0.58
     शर्त
    0.58
     pessoa
    0.57
     tact
    0.57
     person
    0.56
     Plague
    0.55
    E
    0.55
    টাই
    0.55
    Verdict
    0.53
    POSITIVE LOGITS
     بندی
    1.30
    ごとに
    1.13
     단위
    1.08
     subsections
    1.02
     구간
    1.01
     Divid
    0.98
     intervals
    0.98
     spacers
    0.98
    마다
    0.98
     consecutively
    0.97
    Act Density 0.743%

    No Known Activations