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

    Neuronpedia

    INDEX
    Explanations

    S- words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ્સ
    0.85
     eternal
    0.85
    то
    0.82
    sch
    0.82
     sights
    0.79
    sph
    0.79
    t
    0.78
    sor
    0.77
    tog
    0.74
    rupa
    0.73
    POSITIVE LOGITS
    ources
    0.93
    htein
    0.91
    ourcing
    0.90
    ponsors
    0.88
    qrt
    0.86
    pecial
    0.83
    olver
    0.82
    afe
    0.82
     ⿱
    0.82
    queeze
    0.81
    Act Density 0.431%

    No Known Activations