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

    Neuronpedia

    INDEX
    Explanations

    expressions related to programming and coding logic

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

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.84
    ंदीखरीदारी
    -0.82
     pinulongan
    -0.75
    تقاوى
    -0.73
     Roskov
    -0.69
    sizeCache
    -0.68
     Autorizaciones
    -0.67
     Autorisations
    -0.67
    -0.66
    EDEFAULT
    -0.65
    POSITIVE LOGITS
    IntoConstraints
    0.32
    tawesome
    0.31
     linear
    0.30
     démocratie
    0.29
     démocratique
    0.28
     Banken
    0.27
    êté
    0.26
    tazione
    0.26
     Blooms
    0.26
    voorbeeld
    0.26
    Act Density 0.158%

    No Known Activations