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

    Neuronpedia

    INDEX
    Explanations

    adjectives ending in -ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SetValue
    -0.07
    -ft
    -0.07
     никто
    -0.06
     校
    -0.06
     Everyone
    -0.06
     Crate
    -0.06
     overall
    -0.06
    l
    -0.06
     nobody
    -0.06
     kinds
    -0.06
    POSITIVE LOGITS
    ous
    0.10
    ious
    0.09
     dostup
    0.08
    ulous
    0.08
     tas
    0.08
    IOUS
    0.08
    US
    0.08
    ivos
    0.07
    icious
    0.07
    aceous
    0.07
    Act Density 0.065%

    No Known Activations