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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and their various formats

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

    Tokens followed by "0" or another hexadecimal number

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.83
    MessageTagHelper
    -0.79
    ⓧ
    -0.75
     <>",
    -0.74
     ddelweddau
    -0.73
    енча
    -0.67
    TestingModule
    -0.65
     imprimée
    -0.65
     فريبيس
    -0.62
    webElement
    -0.59
    POSITIVE LOGITS
    enumi
    0.60
    convertView
    0.55
    ience
    0.53
    ~/
    0.48
    ukov
    0.47
    läufe
    0.46
    wikidata
    0.46
    āci
    0.45
    truth
    0.45
    tauan
    0.45
    Act Density 0.070%

    No Known Activations