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

    Neuronpedia

    INDEX
    Explanations

    tools and modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mandar
    0.83
    糉
    0.80
     racconto
    0.79
     confine
    0.79
     badger
    0.79
    ıyor
    0.78
     Apps
    0.78
    ڈنگ
    0.77
     furiously
    0.77
    requests
    0.77
    POSITIVE LOGITS
    č
    0.86
    적이
    0.76
    aine
    0.75
    i
    0.74
    刃
    0.72
    ча
    0.71
    ยก
    0.71
    zaam
    0.70
    ก
    0.70
    적
    0.70
    Act Density 0.000%

    No Known Activations