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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INCLUDED
    -0.07
    מסמכי
    -0.07
    嶲
    -0.07
    经营范围
    -0.06
     conspicuous
    -0.06
    .TXT
    -0.06
    roz
    -0.06
     Sponsor
    -0.06
    Appearance
    -0.06
    _cont
    -0.06
    POSITIVE LOGITS
    ollection
    0.07
     separation
    0.07
    fifo
    0.07
    omet
    0.07
     Detection
    0.07
    不忍
    0.07
     universal
    0.07
     Nas
    0.07
    ഫ
    0.07
     fib
    0.06
    Act Density 0.002%

    No Known Activations