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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and notation related to programming and data structures

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

    [@ followed by B or CR and digit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.87
    ロウィン
    -0.84
    TagMode
    -0.84
    featureID
    -0.81
     snippetHide
    -0.79
     ब्रेकडाउन
    -0.79
     مرئيه
    -0.79
     informée
    -0.79
     NSCoder
    -0.78
    ſchaft
    -0.77
    POSITIVE LOGITS
     for
    0.40
    The
    0.39
     Usaha
    0.39
    #
    0.38
    •
    0.38
    [
    0.36
     flèche
    0.35
    在
    0.34
    Local
    0.34
    Base
    0.34
    Act Density 0.777%

    No Known Activations