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
     oi
    -0.08
     wor
    -0.07
     drawback
    -0.07
     كيف
    -0.07
    vol
    -0.06
     швид
    -0.06
     seven
    -0.06
    にな
    -0.06
    _guard
    -0.06
     bracelet
    -0.06
    POSITIVE LOGITS
    NYSE
    0.06
    ught
    0.06
    搭
    0.06
    품
    0.06
    /vendors
    0.06
    uji
    0.06
    ंध
    0.06
     줄
    0.06
    ション
    0.06
     Props
    0.06
    Act Density 0.013%

    No Known Activations