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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight various aspects and types of objects or ideas

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

    a followed by descriptive noun/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     armée
    -0.32
     carriera
    -0.30
     pály
    -0.29
     đứa
    -0.29
     seguida
    -0.29
    Pengertian
    -0.29
     tavola
    -0.29
     amarillas
    -0.28
     demas
    -0.27
     actualidad
    -0.27
    POSITIVE LOGITS
     '\\;'
    0.89
    tanleria
    0.84
     ujednoznacz
    0.84
    RectangleBorder
    0.75
    تقاوى
    0.75
    featureID
    0.71
    titleMargin
    0.71
    httphttps
    0.71
    ThroughAttribute
    0.71
     betweenstory
    0.70
    Act Density 0.027%

    No Known Activations