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

    Neuronpedia

    INDEX
    Explanations

    Attributes and traits

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atmosphere
    2.95
     mood
    2.72
    atmosphere
    2.63
     Atmosphere
    2.63
     atmos
    2.56
     Atmosphäre
    2.50
     tone
    2.48
     atmospheres
    2.41
    Atm
    2.40
     atmosfera
    2.39
    POSITIVE LOGITS
     DeepCollection
    0.65
     dày
    0.63
    ūk
    0.60
    inggi
    0.58
    uvu
    0.57
     Correspondent
    0.56
     disadvant
    0.56
    inelli
    0.56
     downs
    0.56
     baffle
    0.56
    Act Density 0.103%

    No Known Activations