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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _merged
    -0.07
    аша
    -0.06
     meet
    -0.06
    orre
    -0.06
     warning
    -0.06
    реть
    -0.06
    Happy
    -0.06
     toolbox
    -0.06
    Sep
    -0.06
    Could
    -0.06
    POSITIVE LOGITS
     embroidery
    0.07
    ichael
    0.06
    ('<
    0.06
     vàng
    0.06
     Crusher
    0.06
     resetting
    0.06
     muscular
    0.06
    folios
    0.06
     didReceiveMemoryWarning
    0.06
    (skill
    0.06
    Act Density 0.056%

    No Known Activations