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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tickets
    -0.07
    یل
    -0.07
     minh
    -0.07
     receiving
    -0.06
     embarrassed
    -0.06
    ERIC
    -0.06
    wx
    -0.06
    ンの
    -0.06
    ็กซ
    -0.06
     accompanied
    -0.06
    POSITIVE LOGITS
     Appalachian
    0.07
    .KeyPress
    0.07
    .Rectangle
    0.07
    .Fill
    0.06
     شکن
    0.06
    .par
    0.06
     ธ
    0.06
     Voc
    0.06
     TripAdvisor
    0.06
    .Long
    0.06
    Act Density 0.075%

    No Known Activations