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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utura
    -0.07
     הקו
    -0.07
    уще
    -0.07
    階段
    -0.06
     Wo
    -0.06
     texture
    -0.06
     представлен
    -0.06
     Việc
    -0.06
    relative
    -0.06
     innings
    -0.06
    POSITIVE LOGITS
    会让你
    0.07
    "https
    0.07
    ......↵↵
    0.07
    _REMOVE
    0.07
    kiye
    0.07
    ToLeft
    0.07
    识
    0.07
    leftJoin
    0.07
    😷
    0.07
    _LENGTH
    0.06
    Act Density 0.035%

    No Known Activations