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

    Neuronpedia

    INDEX
    Explanations

    quantum computing, algorithms, attention mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paragraphs
    0.43
     newline
    0.42
     paragraphs
    0.41
     par
    0.39
    noindent
    0.39
    বন্ধন
    0.38
    multicol
    0.38
    णियों
    0.38
    ueve
    0.38
    ≥</
    0.38
    POSITIVE LOGITS
     stretch
    0.61
     stretching
    0.55
    stretch
    0.52
     Stretch
    0.52
     Ones
    0.52
     Stretching
    0.50
     One
    0.47
     Dub
    0.47
     stretched
    0.46
    Dub
    0.46
    Act Density 0.000%

    No Known Activations