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

    Neuronpedia

    INDEX
    Explanations

    arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     successes
    -0.08
     Cycle
    -0.08
     protagonists
    -0.08
     máy
    -0.07
    臺
    -0.07
     linux
    -0.07
     Opportunities
    -0.07
     સમાવ
    -0.07
     lego
    -0.07
    (lo
    -0.07
    POSITIVE LOGITS
     skepticism
    0.09
    观点
    0.08
     zahtev
    0.08
    觉得
    0.08
     obsession
    0.08
    views
    0.08
    ాన్ని
    0.08
    认为
    0.08
     skept
    0.07
    crast
    0.07
    Act Density 0.004%

    No Known Activations