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

    Neuronpedia

    INDEX
    Explanations

    java code with `toLowerCase` and references to "filter" and numerical comparisons

    oai_token-act-pair · gemini-2.0-flash

    unusual or non-standard text patterns

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.61
     l
    -0.48
    is
    -0.47
     f
    -0.47
    dotti
    -0.45
    Frame
    -0.45
     u
    -0.44
     levure
    -0.44
     pertes
    -0.42
     is
    -0.42
    POSITIVE LOGITS
     ligiloj
    0.95
    Tembelea
    0.94
    клопе
    0.93
    ImageContext
    0.93
    ########.
    0.91
    SequentialGroup
    0.90
    énario
    0.90
    تقاوى
    0.89
     للاسماء
    0.88
     Monfieur
    0.87
    Act Density 0.504%

    No Known Activations