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

    Neuronpedia

    INDEX
    Explanations

    exclamatory phrases and promotional offers

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

    starting a new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matig
    -0.32
    verson
    -0.31
    kaka
    -0.31
    bootstrapcdn
    -0.31
     Wirken
    -0.30
    ICATION
    -0.30
    halen
    -0.30
     konkret
    -0.30
    haj
    -0.30
    amazonaws
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.62
    incenti
    0.59
    Incenti
    0.59
     incenti
    0.57
     الحره
    0.56
     ditawarkan
    0.54
     incentive
    0.54
    AddTagHelper
    0.53
    nEnter
    0.53
    bitField
    0.52
    Act Density 0.019%

    No Known Activations