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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    柽
    0.41
    ச்சா
    0.39
    okeh
    0.38
     inégal
    0.37
     পরীক্ষায়
    0.37
     такими
    0.37
    торами
    0.37
    周围
    0.36
     म्हट
    0.36
     काशी
    0.36
    POSITIVE LOGITS
     publishing
    0.42
     waveform
    0.42
    នុ
    0.40
     subtract
    0.38
    ຢ
    0.38
    faculty
    0.37
    Personality
    0.36
    Publish
    0.36
    ளோ
    0.36
    Faculty
    0.36
    Act Density 0.002%

    No Known Activations