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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to statistics and measurements

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

    Numbers within parentheses or ranges

    np_acts-logits-general · gemini-2.0-flash

    numerical ranges and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     small
    -0.88
     niewiel
    -0.85
    small
    -0.78
    Small
    -0.78
     smaller
    -0.77
     Small
    -0.77
     minor
    -0.75
     SMALL
    -0.72
    SMALL
    -0.72
    minor
    -0.70
    POSITIVE LOGITS
    rungsseite
    0.77
     whopping
    0.75
     (>
    0.74
    ormous
    0.69
     متعلقه
    0.68
    aarrggbb
    0.66
     enormous
    0.64
    mybatisplus
    0.64
     vysok
    0.63
     quadruple
    0.63
    Act Density 0.701%

    No Known Activations