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

    Neuronpedia

    INDEX
    Explanations

    hard work, wired, coded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ́u
    0.40
     websocket
    0.39
    atsiya
    0.39
    COLUMN
    0.38
    ڄ
    0.38
    韆
    0.38
     Dahmer
    0.38
    حسن
    0.37
    ｱ
    0.37
    ईद
    0.37
    POSITIVE LOGITS
    coded
    0.92
    wired
    0.92
    boiled
    0.77
    ened
    0.77
    ening
    0.75
    core
    0.73
    wearing
    0.71
    wares
    0.64
    wiring
    0.62
    वेयर
    0.60
    Act Density 0.023%

    No Known Activations