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

    Neuronpedia

    INDEX
    Explanations

    verbs following "She"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ą
    1.70
    t
    1.55
    nz
    1.54
    ない
    1.53
    т
    1.46
    ्य
    1.45
    ات
    1.40
    stä
    1.40
    nq
    1.39
    nú
    1.38
    POSITIVE LOGITS
    ﻟ
    1.33
    єї
    1.23
    pherds
    1.22
    çe
    1.18
    heastern
    1.16
     centrifugal
    1.16
    Slf
    1.13
     तौर
    1.12
     fundador
    1.12
     bedeut
    1.07
    Act Density 0.013%

    No Known Activations