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

    Neuronpedia

    INDEX
    Explanations

    piece

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "fmt
    -0.07
    (comp
    -0.07
    jun
    -0.07
    uter
    -0.06
     znám
    -0.06
    фек
    -0.06
    の人
    -0.06
    往
    -0.06
     elucid
    -0.06
    adioButton
    -0.06
    POSITIVE LOGITS
    underscore
    0.07
     hvis
    0.07
    ']:↵
    0.06
    .Return
    0.06
    	expected
    0.06
    .aggregate
    0.06
    _expected
    0.06
     interiors
    0.06
     surprisingly
    0.06
     Especially
    0.06
    Act Density 0.105%

    No Known Activations