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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certe
    -0.08
     bait
    -0.08
     interdisciplinary
    -0.08
     ord
    -0.08
    ✨
    -0.07
     £
    -0.07
    ěž
    -0.07
    诚
    -0.07
    _ag
    -0.07
    关键词
    -0.07
    POSITIVE LOGITS
     Petroleum
    0.09
     ....↵↵
    0.08
     Returns
    0.08
     ....↵
    0.08
     abusive
    0.08
     ...)
    0.07
    xxx
    0.07
    ・・・
    0.07
     .....
    0.07
    ็ต
    0.07
    Act Density 0.033%

    No Known Activations