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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and numerical results in scientific research

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers ending in 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     III
    -0.54
    larıyla
    -0.46
     IV
    -0.44
    huana
    -0.44
     One
    -0.44
     II
    -0.43
    mipmap
    -0.42
     I
    -0.42
     Two
    -0.42
    -
    -0.41
    POSITIVE LOGITS
     forty
    0.94
     Thirty
    0.94
     thirty
    0.93
     seventy
    0.91
     sixty
    0.91
     Forty
    0.90
    forty
    0.90
    ContentAsync
    0.85
     Seventy
    0.85
     fifty
    0.85
    Act Density 1.008%

    No Known Activations