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

    Neuronpedia

    INDEX
    Explanations

    affirmations and expressions of uncertainty

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

    Sure, but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indépendante
    -0.43
    pexpr
    -0.41
     demikian
    -0.39
     SqlCommand
    -0.36
     vectorielle
    -0.35
    enumi
    -0.35
     Veuillez
    -0.35
     terpisah
    -0.35
     LatLng
    -0.34
     surla
    -0.34
    POSITIVE LOGITS
    PreferredItem
    0.57
    Sure
    0.53
    ंदीखरीदारी
    0.52
    esez
    0.52
    AppComponent
    0.51
     Sure
    0.51
    dafx
    0.48
    ulemon
    0.48
    crombie
    0.48
    ApplicationTests
    0.47
    Act Density 0.030%

    No Known Activations