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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kadın
    -0.08
    iesel
    -0.08
    (sorted
    -0.08
    Country
    -0.07
    .reverse
    -0.07
     comida
    -0.07
     respiratory
    -0.07
    	git
    -0.07
    getId
    -0.07
    ully
    -0.07
    POSITIVE LOGITS
    爆出
    0.07
    丝丝
    0.07
    蟪
    0.07
    форм
    0.07
     Seit
    0.07
    쿨
    0.06
     gpointer
    0.06
     me
    0.06
     ">↵
    0.06
     overclock
    0.06
    Act Density 0.011%

    No Known Activations