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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    理念
    -0.08
     Jay
    -0.08
     spare
    -0.08
     multiprocessing
    -0.07
     Spain
    -0.07
    anyi
    -0.07
     koli
    -0.07
     Win
    -0.07
    enticate
    -0.07
     zee
    -0.07
    POSITIVE LOGITS
    (lp
    0.08
     lp
    0.08
     estím
    0.08
     планы
    0.08
     पूछा
    0.08
     notorious
    0.08
    -solving
    0.08
     самостоятельно
    0.08
    Absolute
    0.07
     абсолют
    0.07
    Act Density 0.060%

    No Known Activations