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

    Neuronpedia

    INDEX
    Explanations

    strong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    哚
    -0.07
    ｅ
    -0.07
    (ln
    -0.07
    认
    -0.07
     części
    -0.06
     translator
    -0.06
    ả
    -0.06
    (:
    -0.06
     Sci
    -0.06
    淡
    -0.06
    POSITIVE LOGITS
    awah
    0.08
     Hitch
    0.08
    'ét
    0.07
     Kaw
    0.07
    .health
    0.07
     logical
    0.07
    כדור
    0.07
     grav
    0.07
     Harr
    0.07
    Cou
    0.07
    Act Density 0.040%

    No Known Activations