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

    Neuronpedia

    INDEX
    Explanations

    dictionary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     felse
    -0.08
    mass
    -0.07
     výstav
    -0.07
     glamour
    -0.06
    aine
    -0.06
     sửa
    -0.06
     Pagination
    -0.06
     Amar
    -0.06
     modne
    -0.06
     prov
    -0.06
    POSITIVE LOGITS
    =dict
    0.08
     Dict
    0.08
     dict
    0.08
    classic
    0.08
    pic
    0.07
     whit
    0.07
    Dict
    0.07
    crypt
    0.07
     picked
    0.07
    .Dictionary
    0.07
    Act Density 0.015%

    No Known Activations