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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	logging
    -0.07
     norms
    -0.07
    vs
    -0.06
     figsize
    -0.06
    Assets
    -0.06
     свят
    -0.06
    _mock
    -0.06
     Notification
    -0.06
    ary
    -0.06
    迹
    -0.06
    POSITIVE LOGITS
    .movies
    0.06
    liste
    0.06
     Pract
    0.06
     RESERVED
    0.06
     PARTY
    0.06
     준
    0.06
     üniversit
    0.06
     соот
    0.06
    -А
    0.06
    -make
    0.06
    Act Density 0.068%

    No Known Activations