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

    Neuronpedia

    INDEX
    Explanations

    data matching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fond
    -0.07
    -element
    -0.07
     robust
    -0.07
     ô
    -0.06
    _SUS
    -0.06
     알고
    -0.06
    荇
    -0.06
     Ingredient
    -0.06
    來
    -0.06
    Codec
    -0.06
    POSITIVE LOGITS
    SPACE
    0.07
     🙂
    0.07
    language
    0.07
    Favorites
    0.07
    (\
    0.07
    成了
    0.07
     atop
    0.07
    ●
    0.06
    PRIVATE
    0.06
     sociales
    0.06
    Act Density 0.046%

    No Known Activations