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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     METHODS
    -0.07
    Wild
    -0.06
    쇼
    -0.06
     Evening
    -0.06
    Geom
    -0.06
     Wild
    -0.06
    @Path
    -0.06
    plant
    -0.06
    Ин
    -0.06
    Notes
    -0.06
    POSITIVE LOGITS
    171
    0.07
     حکومت
    0.07
     ความ
    0.07
     olmadan
    0.07
     xyz
    0.06
    -kit
    0.06
     최고
    0.06
    یدا
    0.06
    utex
    0.06
    ıza
    0.06
    Act Density 0.000%

    No Known Activations