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

    Neuronpedia

    INDEX
    Explanations

    test levels & types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quatre
    0.97
     жители
    0.92
     menambah
    0.91
    zelfde
    0.91
     celui
    0.88
    maxY
    0.88
     serait
    0.87
    이고
    0.87
    clamp
    0.86
    最小值
    0.86
    POSITIVE LOGITS
    c
    1.03
     molds
    0.84
    ாச
    0.82
     fellowships
    0.75
    ordinator
    0.74
    гуу
    0.72
     príp
    0.70
    }^{*
    0.70
    ジャケット
    0.70
     netherlands
    0.70
    Act Density 0.000%

    No Known Activations