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

    Neuronpedia

    INDEX
    Explanations

    W3Schools content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ingle
    0.46
     switch
    0.45
    rd
    0.43
    hens
    0.42
    f
    0.42
     switched
    0.40
    tf
    0.40
    elves
    0.39
    d
    0.39
    art
    0.39
    POSITIVE LOGITS
    BufOffset
    0.46
    評判
    0.45
     लग
    0.43
    Makeup
    0.43
    石頭
    0.42
     מב
    0.41
    ंभ
    0.40
    బి
    0.40
    納得
    0.40
    摶
    0.40
    Act Density 0.001%

    No Known Activations