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

    Neuronpedia

    INDEX
    Explanations

    numerical representations or formats

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

    Numbers in parentheses

    np_acts-logits-general · gemini-2.0-flash

    percentages and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Бахар
    -0.73
    })*/
    -0.60
    Erreferentziak
    -0.58
     متعلقه
    -0.57
    Kanpo
    -0.54
     فريبيس
    -0.53
    endwhile
    -0.53
    potranspiration
    -0.53
    ⮕
    -0.52
    ▼
    -0.51
    POSITIVE LOGITS
    GEBURTSDATUM
    0.58
    ListModule
    0.52
     polvere
    0.49
     doppia
    0.46
     flesta
    0.45
     Mean
    0.45
    TagHelper
    0.44
    fail
    0.43
     perfección
    0.43
     mean
    0.43
    Act Density 0.278%

    No Known Activations