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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    今回は
    0.38
    ongrass
    0.37
     کہنا
    0.36
    다
    0.35
    unts
    0.35
     adage
    0.35
     οδη
    0.35
     United
    0.35
    uncul
    0.35
    ट्टा
    0.35
    POSITIVE LOGITS
    𒊺
    0.49
     müş
    0.46
    ޟ
    0.45
     सुनेंरोक
    0.44
     potenc
    0.43
    ULATORY
    0.43
     obič
    0.43
    猊
    0.43
    𒋀
    0.42
     CIE
    0.42
    Act Density 0.002%

    No Known Activations