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

    Neuronpedia

    INDEX
    Explanations

    Numerical values

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    miyor
    -0.08
    ionic
    -0.06
    acteria
    -0.06
     phot
    -0.06
     یوتی
    -0.06
     žalob
    -0.06
    İng
    -0.06
     Santana
    -0.06
    554
    -0.06
    ixture
    -0.06
    POSITIVE LOGITS
     мої
    0.07
     Music
    0.07
    noop
    0.06
    (this
    0.06
    <head
    0.06
     Exist
    0.06
    舞
    0.06
    OOT
    0.06
     rootReducer
    0.06
     Ft
    0.06
    Act Density 0.084%

    No Known Activations