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

    Neuronpedia

    INDEX
    Explanations

    references to quantitative measures or levels in various contexts

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

    higher order or larger quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.53
     архивлан
    -0.52
    writeHead
    -0.47
     للمعارف
    -0.42
    GEBURTSDATUM
    -0.41
    فحة
    -0.40
     enzymatic
    -0.39
     {!
    -0.38
     Axel
    -0.38
    Malloc
    -0.38
    POSITIVE LOGITS
    Smaller
    1.05
    Larger
    1.01
    higher
    0.93
     Larger
    0.92
    larger
    0.92
    Longer
    0.92
    Higher
    0.92
     bigger
    0.91
    Bigger
    0.91
    faster
    0.91
    Act Density 0.102%

    No Known Activations