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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers associated with data or variables

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

    #define keywords hexadecimal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.67
    .
    -0.49
    {
    -0.45
    t
    -0.44
    [toxicity=0]
    -0.43
     often
    -0.43
     stress
    -0.42
    ing
    -0.42
    s
    -0.42
    ↵↵
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.67
     ainfi
    0.62
     iſt
    0.62
    Manbalar
    0.60
     GoogleFonts
    0.60
    étoit
    0.55
     plufieurs
    0.55
     kasarigan
    0.54
     ſein
    0.53
     ſind
    0.52
    Act Density 0.328%

    No Known Activations