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

    Neuronpedia

    INDEX
    Explanations

    data structures or references related to numerical values or statistics

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

    Numbers in parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gön
    -0.48
     Bon
    -0.44
    izr
    -0.44
    كويكب
    -0.43
    field
    -0.42
    HasAnnotation
    -0.42
    Bon
    -0.41
     szóci
    -0.41
    américa
    -0.41
    uma
    -0.40
    POSITIVE LOGITS
    afficheront
    0.75
    ConstraintMaker
    0.73
    rungsseite
    0.67
    kháu
    0.65
     XCTest
    0.59
     SwitchCompat
    0.59
    DockStyle
    0.59
    expandindo
    0.58
    rapeau
    0.58
     VIDEOTAPE
    0.58
    Act Density 0.570%

    No Known Activations