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

    Neuronpedia

    INDEX
    Explanations

    file paths, application data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lifting
    -0.07
    ода
    -0.07
    ופ
    -0.07
    .method
    -0.07
    ൈ
    -0.07
     착
    -0.07
     senses
    -0.07
     경제
    -0.07
     waterfall
    -0.07
     perfectly
    -0.07
    POSITIVE LOGITS
     ~/.
    0.10
     Cookies
    0.09
    Cookies
    0.09
    cookies
    0.09
    .cookies
    0.09
    DATA
    0.09
    Legacy
    0.09
     cookies
    0.09
     legacy
    0.08
    otheken
    0.08
    Act Density 0.008%

    No Known Activations