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

    Neuronpedia

    INDEX
    Explanations

    etric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nap
    -0.06
    .WebServlet
    -0.06
    $r
    -0.06
    	widget
    -0.06
     spoilers
    -0.06
    receive
    -0.06
     winds
    -0.06
    pone
    -0.06
    _INFORMATION
    -0.06
    /py
    -0.06
    POSITIVE LOGITS
     mocked
    0.07
     knocked
    0.07
    (KEY
    0.07
     Rowling
    0.06
     �
    0.06
     jednoduch
    0.06
     immer
    0.06
     сок
    0.06
     вигля
    0.06
    认
    0.06
    Act Density 0.004%

    No Known Activations