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

    Neuronpedia

    INDEX
    Explanations

    starts of phrases or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ウト
    -0.86
    perusahaan
    -0.84
     >
    -0.84
    carrera
    -0.82
     their
    -0.82
     мульти
    -0.82
    dbContext
    -0.82
     roupas
    -0.81
    يم
    -0.80
     Jets
    -0.79
    POSITIVE LOGITS
     garant
    0.84
     घट
    0.83
     Visita
    0.82
    olidation
    0.82
     catégories
    0.81
    何度
    0.81
     GREEK
    0.80
     piz
    0.80
     Forse
    0.80
    such
    0.79
    Act Density 0.002%

    No Known Activations