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

    Neuronpedia

    INDEX
    Explanations

    numbers relating to temperature and water, along with possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    specialized vocabulary related to scientific or technical contexts

    np_token-act-pair-logits · gpt-4o-mini

    Celsius temperatures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Degree
    -0.54
     froide
    -0.54
     degrés
    -0.53
     pulumi
    -0.53
    denk
    -0.51
     Temp
    -0.49
     velkommen
    -0.49
     Warming
    -0.49
     GoogleFonts
    -0.49
     Temperature
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.96
    出版年
    0.73
    Portail
    0.71
    GraphicsUnit
    0.70
    TagHelper
    0.64
    InjectAttribute
    0.62
    KURZBESCHREIBUNG
    0.62
     مرئيه
    0.59
    AuthContext
    0.59
    Datuak
    0.59
    Act Density 0.864%

    No Known Activations