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

    Neuronpedia

    INDEX
    Explanations

    bra-ket notation `|ψ⟩`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    la
    0.98
    3
    0.86
    ا
    0.78
     а
    0.76
    ки
    0.76
    ק
    0.75
    ்ப
    0.74
    -
    0.73
    https
    0.71
    স
    0.71
    POSITIVE LOGITS
    也
    0.91
    是
    0.86
    는
    0.85
    வின்
    0.83
     Phòng
    0.81
    ยุ
    0.80
    是从
    0.80
    是谁
    0.77
    IServerGame
    0.75
    मधील
    0.73
    Act Density 0.011%

    No Known Activations