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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fascination
    -0.07
    مان
    -0.06
    Row
    -0.06
     flair
    -0.06
    .Drop
    -0.06
    -fi
    -0.06
     gross
    -0.06
     Wheeler
    -0.06
    ellar
    -0.06
    中文字幕
    -0.06
    POSITIVE LOGITS
     FPGA
    0.08
    /es
    0.07
     Boca
    0.07
    ecd
    0.07
    .SetInt
    0.06
    تبة
    0.06
    �
    0.06
    annotate
    0.06
    )&&
    0.06
    Trading
    0.06
    Act Density 0.026%

    No Known Activations