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

    Neuronpedia

    INDEX
    Explanations

    sparse matrices and graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.68
     not
    0.67
    </h6>
    0.66
    อาหาร
    0.61
     אַ
    0.61
     Hy
    0.60
     ইন্ড
    0.59
     அகற்ற
    0.58
     ט
    0.58
    ını
    0.57
    POSITIVE LOGITS
    '
    0.87
    ном
    0.70
    Cells
    0.64
    while
    0.63
    지
    0.61
    Dense
    0.60
    Datetime
    0.60
    Galer
    0.60
     বলেও
    0.59
    Mack
    0.59
    Act Density 0.004%

    No Known Activations