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
    感
    -0.08
     lành
    -0.06
     desar
    -0.06
    -first
    -0.06
    ----↵↵
    -0.06
    ('\\
    -0.06
     sphere
    -0.06
     "":↵
    -0.06
     côt
    -0.06
     در
    -0.06
    POSITIVE LOGITS
     Residence
    0.07
     Rebel
    0.06
     excessive
    0.06
    чої
    0.06
     nghiên
    0.06
    ow
    0.06
    utenant
    0.06
    reck
    0.06
     parti
    0.06
    /code
    0.06
    Act Density 0.004%

    No Known Activations