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

    Neuronpedia

    INDEX
    Explanations

    released, collect, or deploy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     종
    0.38
    공
    0.38
    числения
    0.38
    秥
    0.38
    числе
    0.38
    洳
    0.38
    forderungen
    0.38
     informasjon
    0.38
     অর্ধেক
    0.37
     அறிக
    0.37
    POSITIVE LOGITS
     assassins
    0.41
    FL
    0.40
    ZT
    0.39
     Palazzo
    0.39
    acci
    0.38
     catalysts
    0.38
     annoyed
    0.38
     standing
    0.37
    FI
    0.37
    ola
    0.37
    Act Density 0.000%

    No Known Activations