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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to boolean values in code

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

    French, Polish, and Dutch words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.73
    MLLoader
    -0.59
     Wiktionnaire
    -0.57
    GEBURTSDATUM
    -0.57
     PUBLICATIONS
    -0.57
    SceneManagement
    -0.55
    ThemeOverlay
    -0.53
    脚注の使い方
    -0.52
     continúas
    -0.52
     @"/
    -0.51
    POSITIVE LOGITS
     africains
    0.65
     voisins
    0.62
     hâte
    0.61
     veranderen
    0.60
     concernés
    0.59
     pitié
    0.59
     avoient
    0.57
     démocr
    0.57
     chrétiens
    0.57
     zmian
    0.55
    Act Density 0.009%

    No Known Activations