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

    Neuronpedia

    INDEX
    Explanations

    silent film

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mínima
    -0.86
    houettes
    -0.85
     Reeve
    -0.84
    că
    -0.84
     reality
    -0.84
     lingü
    -0.83
    entur
    -0.82
    Forza
    -0.81
    呪術
    -0.79
     to
    -0.79
    POSITIVE LOGITS
     Silent
    1.89
     silent
    1.80
    Silent
    1.71
    silent
    1.68
     silen
    1.43
     SIL
    1.40
     silently
    1.20
    SIL
    1.11
    Sil
    1.10
     Silence
    1.09
    Act Density 0.011%

    No Known Activations