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

    Neuronpedia

    INDEX
    Explanations

    emoticons and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Techniques
    -0.06
     EnumerableStream
    -0.06
    progressbar
    -0.06
     dinner
    -0.06
    细
    -0.06
    _neighbor
    -0.06
    취
    -0.06
    width
    -0.06
    Tracks
    -0.06
     Edwin
    -0.06
    POSITIVE LOGITS
    cción
    0.07
    classify
    0.07
     veriyor
    0.07
    fé
    0.07
    λή
    0.06
    _EM
    0.06
    \'
    0.06
    _dd
    0.06
     OECD
    0.06
    bage
    0.06
    Act Density 0.042%

    No Known Activations