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

    Neuronpedia

    INDEX
    Explanations

    skin tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ленні
    0.51
    ؤال
    0.49
     санк
    0.45
     زمانی
    0.44
    ități
    0.44
     положения
    0.44
     одино
    0.43
     davantage
    0.43
     импуль
    0.43
     mãi
    0.43
    POSITIVE LOGITS
     layer
    1.42
     layers
    1.29
    层
    1.14
    layer
    1.13
     thickness
    1.09
     Layers
    1.06
     coating
    1.05
     слой
    1.04
     Layer
    1.03
    層
    1.02
    Act Density 0.136%

    No Known Activations