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

    Neuronpedia

    INDEX
    Explanations

    expressions of quantity and comparisons

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

    quantities and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wußt
    -0.49
     kvinder
    -0.47
     montagna
    -0.44
     człowie
    -0.42
     Konsequ
    -0.41
     sukienka
    -0.41
     maternidade
    -0.41
     iluminação
    -0.40
     atardecer
    -0.40
     üz
    -0.40
    POSITIVE LOGITS
     oprot
    0.45
    fromnode
    0.44
    VersionUID
    0.44
     Vikipedi
    0.43
    enterOuterAlt
    0.43
    uisine
    0.43
    epam
    0.42
     مشارکت‌کنندگان
    0.42
     spell
    0.41
    GraphicsUnit
    0.41
    Act Density 0.094%

    No Known Activations