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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    靬
    -0.08
    胛
    -0.07
    (Scene
    -0.07
     Ish
    -0.07
     Rt
    -0.07
    עץ
    -0.07
     perg
    -0.07
    国土
    -0.07
    (void
    -0.07
    ⵣ
    -0.07
    POSITIVE LOGITS
    rimon
    0.07
     flavorful
    0.07
     açıl
    0.07
     AUT
    0.07
    usty
    0.07
     flavors
    0.07
    fections
    0.07
    Friendly
    0.06
     Lowest
    0.06
     lovely
    0.06
    Act Density 0.086%

    No Known Activations