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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Countdown
    -0.08
    law
    -0.08
     Countdown
    -0.07
     Meadows
    -0.07
    ellen
    -0.07
    Lady
    -0.07
     Goddess
    -0.07
    Leadership
    -0.07
     kuris
    -0.07
     лидер
    -0.07
    POSITIVE LOGITS
     typically
    0.12
     hundreds
    0.12
     thousands
    0.12
    typically
    0.12
     millions
    0.11
    Typically
    0.11
     бывает
    0.11
     Typically
    0.11
    几十
    0.11
     few
    0.10
    Act Density 0.033%

    No Known Activations