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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jo
    -0.07
    >ID
    -0.06
     HE
    -0.06
    oxide
    -0.06
    _fh
    -0.06
     tutto
    -0.06
     sentencing
    -0.06
    yat
    -0.06
    -з
    -0.06
    ,application
    -0.06
    POSITIVE LOGITS
     Dolphins
    0.07
     док
    0.07
     Maven
    0.07
    ึ้
    0.07
    _dummy
    0.07
     radar
    0.07
     olmasına
    0.06
     internet
    0.06
     drones
    0.06
     藤
    0.06
    Act Density 0.007%

    No Known Activations