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

    Neuronpedia

    INDEX
    Explanations

    math/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    David
    -0.07
     낮
    -0.07
     Kun
    -0.07
    Jud
    -0.06
     David
    -0.06
    으로
    -0.06
     CROSS
    -0.06
    delimiter
    -0.06
    แค
    -0.06
    ін
    -0.06
    POSITIVE LOGITS
     Ammo
    0.06
    ераль
    0.06
    (&_
    0.06
     specials
    0.06
    .Last
    0.06
    wing
    0.06
    ेटर
    0.06
    394
    0.06
    'elle
    0.06
    psc
    0.06
    Act Density 0.037%

    No Known Activations