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

    Neuronpedia

    INDEX
    Explanations

    function descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     انشاء
    0.38
     excelled
    0.38
     싱
    0.38
     exacerb
    0.38
    Sad
    0.38
     நடைபெறும்
    0.38
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.37
    Dok
    0.37
    ेंड
    0.37
    0.37
    POSITIVE LOGITS
    ivi
    0.40
    categoryId
    0.38
     ঠ
    0.38
     Wheaton
    0.37
     instant
    0.36
     дово
    0.36
     کی
    0.35
    yección
    0.35
    挛
    0.35
    总部
    0.34
    Act Density 0.001%

    No Known Activations