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

    Neuronpedia

    INDEX
    Explanations

    colons/curly braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Estimated
    -0.07
     unset
    -0.07
     warnings
    -0.07
    rav
    -0.07
     estão
    -0.06
     업데이트
    -0.06
    	active
    -0.06
    เร
    -0.06
    رض
    -0.06
     speaker
    -0.06
    POSITIVE LOGITS
     CWE
    0.09
     Gratuit
    0.06
    highest
    0.06
     Bbw
    0.06
    Equals
    0.06
    χω
    0.06
    placer
    0.06
    аблиц
    0.06
    ?key
    0.06
     Ges
    0.06
    Act Density 0.003%

    No Known Activations