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

    Neuronpedia

    INDEX
    Explanations

    the word "highly" and words near it, but not consistently

    oai_token-act-pair · gemini-2.0-flash

    highly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حياتها
    -0.61
     désormais
    -0.57
    volmente
    -0.56
     découver
    -0.54
    eaways
    -0.54
    lıkla
    -0.54
    EndInit
    -0.53
     totally
    -0.53
     Super
    -0.52
     leçons
    -0.52
    POSITIVE LOGITS
    клопе
    0.72
     surla
    0.58
    تقاوى
    0.52
    DoubleQuotes
    0.52
     placebo
    0.52
    Filmografie
    0.52
     unpopular
    0.51
     sugges
    0.51
    dataclass
    0.51
     Teut
    0.50
    Act Density 0.234%

    No Known Activations