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

    Neuronpedia

    INDEX
    Explanations

    French phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sights
    -0.06
    =%
    -0.06
    webs
    -0.06
     disadvantage
    -0.06
    默认
    -0.06
     foo
    -0.06
     census
    -0.06
     libr
    -0.06
    .release
    -0.06
    Med
    -0.06
    POSITIVE LOGITS
    /init
    0.07
     motto
    0.07
    seniz
    0.07
     flying
    0.07
    plemented
    0.06
     alph
    0.06
     práva
    0.06
    제
    0.06
    /plugins
    0.06
     socially
    0.06
    Act Density 0.032%

    No Known Activations