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

    Neuronpedia

    INDEX
    Explanations

    articles and indicators of strong entity references

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

    "A" followed by descriptive adjectives

    np_acts-logits-general · gemini-2.0-flash

    a singular instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    openqa
    -0.71
     useParams
    -0.60
     Abp
    -0.60
    RunAsync
    -0.59
    principalTable
    -0.56
    orean
    -0.55
    ANCIA
    -0.55
    ADELPHIA
    -0.54
    closedir
    -0.53
    jsonwebtoken
    -0.53
    POSITIVE LOGITS
    Personendaten
    0.78
     few
    0.74
     مشين
    0.67
     good
    0.67
    few
    0.64
     fleste
    0.62
     récente
    0.61
     majority
    0.61
     recent
    0.60
    good
    0.57
    Act Density 0.309%

    No Known Activations