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

    Neuronpedia

    INDEX
    Explanations

    punctuation symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    劢
    -0.07
    DidAppear
    -0.07
    hra
    -0.06
    敏锐
    -0.06
     Licensed
    -0.06
     учеб
    -0.06
     Sistema
    -0.06
     ICU
    -0.06
     gute
    -0.06
    Sele
    -0.06
    POSITIVE LOGITS
     strike
    0.07
    standing
    0.07
    ומים
    0.07
     chords
    0.07
     nonetheless
    0.06
    .stop
    0.06
     sought
    0.06
    (world
    0.06
    健康产业
    0.06
     striped
    0.06
    Act Density 0.035%

    No Known Activations