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

    Neuronpedia

    INDEX
    Explanations

    Eratosthenes, Text to Columns, docx, citation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     POSSIBILITY
    0.55
    ک
    0.51
     ლ
    0.50
     چندین
    0.50
    ພວກເຮົາ
    0.50
    Մ
    0.49
    ходят
    0.48
    ペア
    0.48
    Fg
    0.48
    キャップ
    0.48
    POSITIVE LOGITS
    end
    0.49
    riving
    0.47
    ängen
    0.46
    å
    0.45
    networking
    0.45
    ate
    0.44
    attering
    0.43
    node
    0.42
    ր
    0.41
    ές
    0.41
    Act Density 0.004%

    No Known Activations