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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and expressions related to data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.71
    MLLoader
    -0.65
     GenerationType
    -0.61
    mobileqq
    -0.58
    ագրություններ
    -0.57
    IndentedString
    -0.55
    RTLI
    -0.54
     JpaRepository
    -0.54
     الرياضيه
    -0.49
     يتيمه
    -0.48
    POSITIVE LOGITS
    forhold
    0.43
    chiali
    0.35
     negativos
    0.35
    ้งาน
    0.34
     istrinya
    0.34
     tebal
    0.33
     kteří
    0.33
    merzen
    0.32
     opge
    0.32
    SPATH
    0.31
    Act Density 0.158%

    No Known Activations