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

    Neuronpedia

    INDEX
    Explanations

    say "kind"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     councillors
    -0.07
     setSearch
    -0.07
     cola
    -0.07
    translate
    -0.07
     rozwiązania
    -0.07
    anker
    -0.07
     месяцев
    -0.07
     VN
    -0.07
     amor
    -0.07
    conc
    -0.07
    POSITIVE LOGITS
    蝲
    0.07
    Back
    0.07
     arm
    0.07
    寓意
    0.07
    獻
    0.07
     xml
    0.06
     floral
    0.06
    いただく
    0.06
    ธรรม
    0.06
     Tut
    0.06
    Act Density 0.009%

    No Known Activations