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

    Neuronpedia

    INDEX
    Explanations

    mixed languages and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сильно
    -0.08
     Со
    -0.08
     വിത
    -0.08
     slaan
    -0.07
     những
    -0.07
     games
    -0.07
     тысяч
    -0.07
     bisan
    -0.07
     markedly
    -0.07
     unexpected
    -0.07
    POSITIVE LOGITS
    /Dialog
    0.08
     Groove
    0.08
    \a
    0.08
    aced
    0.07
    사용
    0.07
    BCD
    0.07
    für
    0.07
    ritel
    0.07
    (rad
    0.07
    mas
    0.07
    Act Density 0.000%

    No Known Activations