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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or entities mentioned in a text

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

    following certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.70
    Personensuche
    -0.69
    abestanden
    -0.68
    الإنجليزية
    -0.62
    SharedCtor
    -0.60
    RegistryLite
    -0.59
     esternos
    -0.58
    saraba
    -0.56
    AddTagHelper
    -0.56
    MessageTagHelper
    -0.54
    POSITIVE LOGITS
     препратки
    0.35
     drama
    0.34
    XmlAccessorType
    0.31
    liferay
    0.31
     Hecht
    0.30
    __()
    0.29
     reflected
    0.29
     peran
    0.28
    glGet
    0.28
    Disney
    0.28
    Act Density 0.499%

    No Known Activations