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

    Neuronpedia

    INDEX
    Explanations

    structural elements in computer code or data format

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

    Tokens followed by "__u" or "__be" (likely C code related)

    np_acts-logits-general · gemini-2.0-flash

    unsigned integer types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.63
     JpaRepository
    -0.62
     становника
    -0.58
    ItemBackground
    -0.55
     createSlice
    -0.53
     ambao
    -0.53
    StringProperty
    -0.51
     peccato
    -0.51
     naselje
    -0.51
    iNdEx
    -0.51
    POSITIVE LOGITS
    tagHelper
    0.93
     utafitiHapana
    0.72
    Билгалдахарш
    0.71
    (!__
    0.68
     وتسجيلات
    0.67
    addComponent
    0.67
    tagHelperRunner
    0.67
    (__
    0.67
     (__
    0.64
    heritance
    0.63
    Act Density 0.037%

    No Known Activations