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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contests
    -0.07
    tool
    -0.07
     basePath
    -0.07
    .peek
    -0.07
     ceremony
    -0.07
    _QUESTION
    -0.07
    佸
    -0.07
    קט
    -0.07
    来て
    -0.07
    打猎
    -0.06
    POSITIVE LOGITS
     ?:
    0.07
     עמוק
    0.07
    _Click
    0.07
    /release
    0.07
    .addMouseListener
    0.06
    宇宙
    0.06
    calloc
    0.06
    笔
    0.06
    쟎
    0.06
    路由器
    0.06
    Act Density 0.035%

    No Known Activations