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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     собой
    -0.06
    .setdefault
    -0.06
     other
    -0.06
     Phelps
    -0.06
     интерес
    -0.06
     playlists
    -0.06
     пром
    -0.06
     Holt
    -0.06
    _H
    -0.06
    Singapore
    -0.06
    POSITIVE LOGITS
     af
    0.07
    <class
    0.07
     striped
    0.06
    _shader
    0.06
    	length
    0.06
    -drive
    0.06
    adium
    0.06
    ari
    0.06
    ......↵↵
    0.06
     пы
    0.06
    Act Density 0.184%

    No Known Activations