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

    Neuronpedia

    INDEX
    Explanations

    manual or physical actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝔯
    0.36
     Terima
    0.36
    复杂度
    0.35
     ristrutt
    0.33
     chhoti
    0.33
     శ్రీ
    0.32
     پیپلز
    0.32
     имен
    0.32
     unapolog
    0.32
     כמו
    0.32
    POSITIVE LOGITS
     manually
    0.64
     physically
    0.52
    手动
    0.52
     manualmente
    0.52
     manual
    0.51
     monitor
    0.50
     manuel
    0.45
    手工
    0.43
     вру
    0.43
     Manual
    0.43
    Act Density 0.104%

    No Known Activations