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

    Neuronpedia

    INDEX
    Explanations

    expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    地球
    -0.07
    entr
    -0.07
     duty
    -0.06
    mas
    -0.06
    ynomials
    -0.06
    ajor
    -0.06
    arus
    -0.06
     shelter
    -0.06
    irectory
    -0.06
    _co
    -0.06
    POSITIVE LOGITS
    (tm
    0.07
     Publishing
    0.07
    precedented
    0.07
     Werner
    0.07
    령
    0.06
    );">↵
    0.06
    /epl
    0.06
    !",↵
    0.06
    .Disclaimer
    0.06
     disclosed
    0.06
    Act Density 0.009%

    No Known Activations