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

    Neuronpedia

    INDEX
    Explanations

    phrases describing product specifications and features

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

    Describes product features or qualities

    np_acts-logits-general · gemini-2.0-flash

    designed, available, crafted, constructed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.92
    تقاوى
    -0.76
    الحياه
    -0.75
     дописавши
    -0.73
     незавершена
    -0.72
    principalTable
    -0.70
     الاطلاع
    -0.70
    ValueStyle
    -0.69
    DeleteBehavior
    -0.65
    RegistryLite
    -0.64
    POSITIVE LOGITS
     sure
    0.66
     available
    0.61
     ready
    0.59
     fully
    0.56
     crafted
    0.56
     packed
    0.56
     priced
    0.55
     thoughtfully
    0.55
     designed
    0.55
     meticulously
    0.54
    Act Density 0.127%

    No Known Activations