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

    Neuronpedia

    INDEX
    Explanations

    HTML titles and SEO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	parent
    -0.07
     Clair
    -0.07
    ponce
    -0.07
    Principal
    -0.07
     insulting
    -0.06
    	message
    -0.06
    рест
    -0.06
     مشاركة
    -0.06
     взрос
    -0.06
    -win
    -0.06
    POSITIVE LOGITS
    ":-
    0.06
     shortcuts
    0.06
    CLAIM
    0.06
     flights
    0.06
     질문
    0.06
    noxious
    0.06
    (TYPE
    0.06
    ु
    0.06
     Delay
    0.06
    nou
    0.06
    Act Density 0.007%

    No Known Activations