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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raping
    -0.07
    Stretch
    -0.07
    Path
    -0.07
     Q
    -0.07
    .connector
    -0.06
     successes
    -0.06
     succeeded
    -0.06
    .Mark
    -0.06
    inning
    -0.06
     switches
    -0.06
    POSITIVE LOGITS
     indust
    0.07
    loyment
    0.06
     godt
    0.06
    elry
    0.06
     bekommen
    0.06
     الرسم
    0.06
    ETHOD
    0.06
    bing
    0.06
    .xy
    0.06
    Архівовано
    0.06
    Act Density 0.038%

    No Known Activations