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
    做出
    -0.07
     LIS
    -0.07
     subtle
    -0.06
    _caps
    -0.06
     SOM
    -0.06
    应付
    -0.06
     percussion
    -0.06
     Slovenia
    -0.06
     לצ
    -0.06
    Column
    -0.06
    POSITIVE LOGITS
    =models
    0.07
     Lunar
    0.07
    loop
    0.07
    窖
    0.07
     ładn
    0.07
    uptools
    0.07
    名声
    0.06
    #elif
    0.06
     Ook
    0.06
    ificance
    0.06
    Act Density 0.000%

    No Known Activations