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

    Neuronpedia

    INDEX
    Explanations

    domain range image maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.09
    नुसार
    1.06
    knot
    0.92
    ῎
    0.91
    kach
    0.90
    prend
    0.88
     efectivamente
    0.88
     Alcoholic
    0.87
    m
    0.87
    '
    0.86
    POSITIVE LOGITS
    袭击
    1.09
    出力
    1.04
     indel
    1.04
     kebijakan
    1.02
     привы
    1.02
    디어
    1.02
     productImage
    1.01
    ㎝
    1.00
     başka
    0.98
    勫
    0.98
    Act Density 0.001%

    No Known Activations