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

    Neuronpedia

    INDEX
    Explanations

    greentext convention '>be me'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.11
    ्स
    1.02
    ς
    0.76
     fibers
    0.75
     cort
    0.73
    ாமல்
    0.72
    ים
    0.70
    service
    0.70
     griff
    0.70
     khas
    0.69
    POSITIVE LOGITS
     ﺍ
    0.92
     Furthermore
    0.88
     しかし
    0.88
     但是
    0.84
     muziek
    0.84
     уважаемые
    0.83
    ckiej
    0.83
     调用
    0.83
     Vgl
    0.83
     Asalamualaikum
    0.82
    Act Density 0.001%

    No Known Activations