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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Horm
    -0.09
    _DECLARE
    -0.09
    Gam
    -0.08
     ನಿರ
    -0.08
     mide
    -0.08
    Mat
    -0.08
     lecturers
    -0.07
    Disconnect
    -0.07
     instructors
    -0.07
    stones
    -0.07
    POSITIVE LOGITS
     concernant
    0.10
     regarding
    0.08
     нек
    0.08
     Regarding
    0.08
     하는
    0.08
     dotycz
    0.07
     невер
    0.07
     некоторых
    0.07
    긴
    0.07
     Bons
    0.07
    Act Density 0.000%

    No Known Activations