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

    Neuronpedia

    INDEX
    Explanations

    accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kevin
    -0.07
    .:.
    -0.07
    晓
    -0.06
    민국
    -0.06
    -playing
    -0.06
     WHILE
    -0.06
     QUICK
    -0.06
    ｨ
    -0.06
    リング
    -0.06
     onChanged
    -0.06
    POSITIVE LOGITS
     individually
    0.07
    uly
    0.07
    Та
    0.07
     illegal
    0.06
    Vol
    0.06
    jest
    0.06
     pointing
    0.06
    ne
    0.06
     perfection
    0.06
    porn
    0.06
    Act Density 0.002%

    No Known Activations