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

    Neuronpedia

    INDEX
    Explanations

    Blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rescued
    -0.07
     连
    -0.07
     Heard
    -0.06
    Chan
    -0.06
     сосед
    -0.06
    上げ
    -0.06
     ici
    -0.06
    Cities
    -0.06
    恨
    -0.06
    抽
    -0.06
    POSITIVE LOGITS
    	assertEquals
    0.06
    509
    0.06
     dut
    0.06
    matic
    0.06
     Races
    0.06
     sky
    0.06
    	sort
    0.06
    DOM
    0.06
    _DONE
    0.06
     anom
    0.06
    Act Density 0.038%

    No Known Activations