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

    Neuronpedia

    INDEX
    Explanations

    significant indicators or markers in the context of potential concerns

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

    before numbers

    np_acts-logits-general · gemini-2.0-flash

    higher than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.63
     nahilalakip
    -0.62
    saraba
    -0.61
    CELLANEOUS
    -0.60
     surla
    -0.60
    sieur
    -0.59
    emie
    -0.58
    ThroughAttribute
    -0.56
    uric
    -0.55
    ագրություններ
    -0.55
    POSITIVE LOGITS
    IonicModule
    0.56
    ,
    0.50
    MemoryWarning
    0.49
    XmlRootElement
    0.48
     Signalez
    0.48
    matchCondition
    0.47
     nagu
    0.47
    DropTable
    0.47
     nisso
    0.46
     Préférences
    0.46
    Act Density 0.069%

    No Known Activations