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

    Neuronpedia

    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'яз
    -0.07
    πη
    -0.07
    enzhen
    -0.06
     Buttons
    -0.06
    reak
    -0.06
    object
    -0.06
    Ix
    -0.06
     Fake
    -0.06
    -area
    -0.06
    $order
    -0.06
    POSITIVE LOGITS
     cultiv
    0.08
     пров
    0.06
     decking
    0.06
    PLY
    0.06
    _ability
    0.06
    edir
    0.06
    auce
    0.06
    ับผ
    0.06
     cran
    0.06
     Studi
    0.06
    Act Density 0.000%

    No Known Activations