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

    Neuronpedia

    INDEX
    Explanations

    baking and recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    1.02
    t
    0.98
    وک
    0.93
    ルの
    0.92
    وی
    0.87
    ینگ
    0.87
    ری
    0.86
    f
    0.85
    ﻭ
    0.82
    و
    0.79
    POSITIVE LOGITS
    -
    0.83
     steril
    0.80
     to
    0.79
     at
    0.78
     oven
    0.76
     baking
    0.76
     (
    0.75
     be
    0.75
    ك
    0.74
     Baking
    0.73
    Act Density 0.008%

    No Known Activations