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

    Neuronpedia

    INDEX
    Explanations

    don't hesitate to ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     혹은
    0.44
     또는
    0.43
    이나
    0.42
     Kirsten
    0.42
    锆
    0.41
     Studio
    0.40
     Heidi
    0.40
    θούν
    0.40
     ឬ
    0.40
     следующие
    0.40
    POSITIVE LOGITS
    t
    0.50
    PE
    0.45
    matchCondition
    0.43
    damaged
    0.43
     proizvođa
    0.42
    replaced
    0.41
     manufacturer
    0.41
    PIRE
    0.41
    PR
    0.40
    CLIP
    0.40
    Act Density 0.002%

    No Known Activations