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

    Neuronpedia

    INDEX
    Explanations

    recessed areas/indentations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嫚
    -0.07
     해
    -0.07
    ǝ
    -0.07
     Santiago
    -0.07
    elper
    -0.07
     comprend
    -0.07
    ffffffff
    -0.06
     intercepted
    -0.06
     Crimea
    -0.06
     Chap
    -0.06
    POSITIVE LOGITS
    (IS
    0.08
    R
    0.07
    .hero
    0.07
    atron
    0.07
    Locations
    0.06
    Aura
    0.06
    /private
    0.06
    _Reset
    0.06
    	SET
    0.06
    𓏸
    0.06
    Act Density 0.027%

    No Known Activations