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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    END
    -0.06
    仙
    -0.06
     -------------
    -0.06
    essions
    -0.06
    ós
    -0.06
    -pin
    -0.06
    _EL
    -0.06
    --------↵↵
    -0.06
    ุบ
    -0.06
     nights
    -0.06
    POSITIVE LOGITS
     #↵
    0.06
     Gong
    0.06
    textInput
    0.06
    Single
    0.06
    	reply
    0.06
    chio
    0.06
     rightfully
    0.06
    로운
    0.06
     incompetence
    0.06
     můžete
    0.06
    Act Density 0.049%

    No Known Activations