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
     روم
    -0.07
    onya
    -0.07
    ्पष
    -0.06
    isd
    -0.06
    خبر
    -0.06
     noch
    -0.06
    anye
    -0.06
     پشت
    -0.06
    INST
    -0.06
    _thumbnail
    -0.06
    POSITIVE LOGITS
     UC
    0.07
     TU
    0.07
     leather
    0.07
    دارة
    0.07
     Liu
    0.06
    	active
    0.06
     Images
    0.06
    lacağı
    0.06
     legitimate
    0.06
    (vehicle
    0.06
    Act Density 0.005%

    No Known Activations