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

    Neuronpedia

    INDEX
    Explanations

    adverbs modifying actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polyphen
    1.32
    T
    1.23
     narcotic
    1.21
    बित
    1.15
    する場合
    1.14
    N
    1.14
     prokary
    1.13
     fentanyl
    1.13
     власти
    1.12
     biotechn
    1.09
    POSITIVE LOGITS
    ية
    1.63
    ם
    1.42
    ो
    1.39
    ة
    1.34
    м
    1.34
    ર
    1.33
    ม
    1.32
    нің
    1.30
     ١
    1.27
    ى
    1.26
    Act Density 0.221%

    No Known Activations