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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values and mathematical notations

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

    special characters or formatting elements like tildes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.44
    RTEE
    -0.35
     invokevirtual
    -0.32
     propOrder
    -0.31
     kerül
    -0.30
     Aprend
    -0.30
    initializeApp
    -0.29
    MessageTagHelper
    -0.29
    antası
    -0.28
     Picchu
    -0.28
    POSITIVE LOGITS
    ﹧
    0.56
     OMITBAD
    0.54
     createState
    0.53
    Autoritní
    0.52
    awtextra
    0.51
    〮
    0.51
    Билгалдахарш
    0.50
    EndContext
    0.50
    ropshire
    0.50
    PageContext
    0.49
    Act Density 0.421%

    No Known Activations