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

    Neuronpedia

    INDEX
    Explanations

    taking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    France
    -0.07
     Kul
    -0.07
    oton
    -0.07
    arring
    -0.06
    ibo
    -0.06
    vl
    -0.06
    Чтобы
    -0.06
    yny
    -0.06
    î
    -0.06
     METH
    -0.06
    POSITIVE LOGITS
    	check
    0.07
     mechanic
    0.07
     işlemi
    0.06
     dreams
    0.06
     getResource
    0.06
    .failed
    0.06
    .pic
    0.06
     **/
↵
    0.06
    (tags
    0.06
    )f
    0.06
    Act Density 0.139%

    No Known Activations