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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endir
    -0.07
     hats
    -0.07
    채
    -0.06
    ディース
    -0.06
     Newly
    -0.06
    -tests
    -0.06
    nod
    -0.06
    -To
    -0.06
    ọng
    -0.06
    718
    -0.06
    POSITIVE LOGITS
    ]])↵
    0.07
    Fed
    0.07
    Exceptions
    0.06
    插
    0.06
    +")
    0.06
    ')↵↵↵↵
    0.06
    }*/↵
    0.06
    _playing
    0.06
    (employee
    0.06
     warrior
    0.06
    Act Density 0.071%

    No Known Activations