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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific/journalistic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mb
    -0.07
    (my
    -0.07
     её
    -0.06
    _cart
    -0.06
    せ
    -0.06
    _ru
    -0.06
     pas
    -0.06
    /info
    -0.06
    	selected
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     kteří
    0.07
     hogy
    0.06
    outing
    0.06
    bcc
    0.06
     crashing
    0.06
     mocking
    0.06
     eventually
    0.06
    mazon
    0.06
    Sadly
    0.06
    nia
    0.06
    Act Density 0.096%

    No Known Activations