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

    Neuronpedia

    INDEX
    Explanations

    lines of code and programming constructs

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bangan
    -0.53
    httphttps
    -0.47
    ParallelGroup
    -0.43
    awtextra
    -0.43
    EndInit
    -0.43
    akaian
    -0.41
     }{@
    -0.40
    hombo
    -0.40
     cualquiera
    -0.40
    ském
    -0.38
    POSITIVE LOGITS
     GenerationType
    0.46
     fractions
    0.44
     horizons
    0.43
     circuits
    0.43
    aarrggbb
    0.43
    protoimpl
    0.43
     linkovi
    0.42
    drawSprites
    0.42
     tecniche
    0.42
     attractions
    0.41
    Act Density 0.062%

    No Known Activations