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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dig
    -0.06
     skiing
    -0.06
     周
    -0.06
     başka
    -0.06
    -log
    -0.06
    σχ
    -0.06
     vrai
    -0.06
     imp
    -0.06
    -config
    -0.06
    394
    -0.06
    POSITIVE LOGITS
     rosa
    0.07
     conveniently
    0.07
    整个
    0.06
    BagConstraints
    0.06
    0.06
    Republic
    0.06
    Convert
    0.06
    ...
    0.06
     İz
    0.06
    [Y
    0.06
    Act Density 0.016%

    No Known Activations