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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistical comparisons

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

    Numbers followed by "percent" or "per"

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aktualisiert
    -0.64
    sty
    -0.50
    ilihan
    -0.49
     noexcept
    -0.49
     Placebo
    -0.49
     Rache
    -0.48
    '}}>
    -0.48
     Conserv
    -0.47
     Tapa
    -0.47
    }}/>
    -0.46
    POSITIVE LOGITS
     percent
    1.02
     per
    0.99
     AssemblyCulture
    0.83
     autorytatywna
    0.73
    AndEndTag
    0.72
    IMPORTED
    0.70
    pc
    0.61
     تانيه
    0.60
     pc
    0.58
    ,"
    0.58
    Act Density 0.295%

    No Known Activations