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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values and formatting

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

    Table or matrix formatting

    np_acts-logits-general · gemini-2.0-flash

    code and data tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.51
     ?
    -0.46
     -
    -0.41
    <b>
    -0.40
     bỏ
    -0.40
    <eos>
    -0.40
    ?
    -0.39
     Sy
    -0.39
    1
    -0.39
    GLint
    -0.39
    POSITIVE LOGITS
     للمعارف
    0.97
    tvguidetime
    0.88
     nakalista
    0.85
    省市镇
    0.80
     Проци
    0.79
     betweenstory
    0.78
     فريبيس
    0.78
    bibinfo
    0.74
     CURIAM
    0.73
     بيها
    0.71
    Act Density 0.196%

    No Known Activations