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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {}'.
    -0.07
     comedy
    -0.07
    σταση
    -0.06
    Contr
    -0.06
    CASCADE
    -0.06
    fried
    -0.06
    Nr
    -0.06
    ical
    -0.06
     кто
    -0.06
     Linear
    -0.06
    POSITIVE LOGITS
    .visualization
    0.07
    .best
    0.07
    ),
↵
    0.06
    .switch
    0.06
     clashes
    0.06
     они
    0.06
     coward
    0.06
     {{--<
    0.06
     popped
    0.06
    ;
↵
    0.06
    Act Density 0.019%

    No Known Activations