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

    Neuronpedia

    INDEX
    Explanations

    negative condition descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    USE
    0.44
     narod
    0.44
    は大
    0.42
     glutamate
    0.40
     রোনাল
    0.40
     trưởng
    0.40
    鍑
    0.39
    瞬间
    0.39
     monop
    0.39
     hardware
    0.39
    POSITIVE LOGITS
    ak
    0.53
     zaidi
    0.45
     Казахстан
    0.44
    il
    0.43
    supers
    0.42
     youre
    0.42
    elten
    0.42
    your
    0.41
    akre
    0.41
     /\.
    0.41
    Act Density 0.002%

    No Known Activations