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

    Neuronpedia

    INDEX
    Explanations

    studies and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gestalten
    0.65
    Topic
    0.64
     مسائل
    0.63
     zrozum
    0.62
     kategorii
    0.61
     سیاه
    0.60
     dopln
    0.59
    ่าย
    0.59
     föl
    0.58
    viz
    0.58
    POSITIVE LOGITS
     studies
    1.77
     Studies
    1.56
     research
    1.53
     evidence
    1.49
    studies
    1.46
     reports
    1.44
    Studies
    1.41
     Evidence
    1.36
    研究
    1.33
    research
    1.31
    Act Density 0.617%

    No Known Activations