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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and definitions

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

    Code or math related to matrix operations

    np_acts-logits-general · gemini-2.0-flash

    matrix components and precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoc
    -0.51
    contentLoaded
    -0.51
    JpaRepository
    -0.50
     rius
    -0.50
     nime
    -0.47
    WebElementEntity
    -0.45
     surla
    -0.44
    httphttps
    -0.43
     mendengar
    -0.43
    dengar
    -0.42
    POSITIVE LOGITS
     stride
    0.70
    stride
    0.61
     intptr
    0.60
    GHIJKLM
    0.59
    SharedModule
    0.54
     décal
    0.54
    ImageContext
    0.53
     offsets
    0.53
     block
    0.52
     مرئيه
    0.52
    Act Density 0.523%

    No Known Activations