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

    Neuronpedia

    INDEX
    Explanations

    semester

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    safe
    -0.06
    agation
    -0.06
     зовніш
    -0.06
    	dest
    -0.06
    Consumer
    -0.06
     مالی
    -0.06
    cial
    -0.06
     visceral
    -0.06
     Bitcoins
    -0.06
     Mar
    -0.06
    POSITIVE LOGITS
    –and
    0.07
    /music
    0.07
     {\↵
    0.07
     dialog
    0.06
     holders
    0.06
    -json
    0.06
     ''){↵
    0.06
     respir
    0.06
    (!$
    0.06
     filenames
    0.06
    Act Density 0.000%

    No Known Activations