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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and software integration

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

    works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.61
    minecraftforge
    -0.48
    windowFixed
    -0.47
     faſt
    -0.46
    المشاركات
    -0.44
    Personensuche
    -0.41
     Privacidad
    -0.39
    QtCore
    -0.38
     समीक्षाओं
    -0.38
    ugc
    -0.38
    POSITIVE LOGITS
    correctly
    0.46
     فريبيس
    0.44
    0.43
    0.41
    eterangan
    0.41
     Sidd
    0.39
    outbound
    0.38
    0.38
    "}")
    0.38
    UnsafeEnabled
    0.38
    Act Density 0.045%

    No Known Activations