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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzas
    -0.07
     mansion
    -0.07
     theology
    -0.07
     verifica
    -0.06
    _statistics
    -0.06
    /Sub
    -0.06
    Increasing
    -0.06
    번호
    -0.06
    рин
    -0.06
    Patrick
    -0.06
    POSITIVE LOGITS
    ув
    0.07
    stagram
    0.06
    .amazon
    0.06
    	hash
    0.06
    throws
    0.06
    .argmax
    0.06
     tackled
    0.06
     fate
    0.06
     blossom
    0.06
     Throne
    0.06
    Act Density 0.069%

    No Known Activations