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

    Neuronpedia

    INDEX
    Explanations

    python versions 3.7, 3.8, 3.9, 3.10

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diff
    0.41
     DIFF
    0.41
     """
    0.40
    """
    0.39
    SHIFT
    0.39
     WILLIAM
    0.39
     Halle
    0.38
     trio
    0.38
     үш
    0.38
     rev
    0.38
    POSITIVE LOGITS
     kona
    0.45
    فر
    0.38
     sy
    0.36
     فار
    0.36
    sini
    0.36
    ٨
    0.36
    दम
    0.36
    ピアス
    0.35
    ضح
    0.35
    递
    0.35
    Act Density 0.004%

    No Known Activations