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

    Neuronpedia

    INDEX
    Explanations

    negations or terms conveying the absence of something

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

    without or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.60
    المناصب
    -0.50
    AnchorTagHelper
    -0.46
    Hozzáférés
    -0.46
    EDEFAULT
    -0.45
    parsedMessage
    -0.44
     تانيه
    -0.44
    KURZBESCHREIBUNG
    -0.42
    лтемелер
    -0.41
    XtraReports
    -0.39
    POSITIVE LOGITS
    enumii
    0.50
     bypassing
    0.45
    envolvimento
    0.44
     dependence
    0.42
    lob
    0.42
    enumi
    0.41
    utan
    0.41
    た
    0.40
     dépend
    0.40
    цездатний
    0.40
    Act Density 0.142%

    No Known Activations