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

    Neuronpedia

    INDEX
    Explanations

    get by id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.86
    by
    0.84
    By
    0.74
     By
    0.70
     bằng
    0.65
     бы
    0.61
    ByName
    0.60
    bym
    0.59
    byn
    0.55
    โดย
    0.55
    POSITIVE LOGITS
     adventure
    0.41
     electrolyte
    0.41
    雬
    0.40
     zin
    0.39
     katılı
    0.39
     articul
    0.39
    یی
    0.39
     exfoliating
    0.38
     cutlery
    0.38
     aina
    0.38
    Act Density 0.001%

    No Known Activations