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

    Neuronpedia

    INDEX
    Explanations

    traits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dx
    -0.07
     pickup
    -0.07
    caught
    -0.06
    =_
    -0.06
     ном
    -0.06
    (=)
    -0.06
    allas
    -0.06
     Oliv
    -0.06
    _port
    -0.06
     Mistress
    -0.06
    POSITIVE LOGITS
    ileceği
    0.07
    โจ
    0.06
    154
    0.06
     argc
    0.06
     pracy
    0.06
    duğ
    0.06
    (prob
    0.06
    Ả
    0.06
    AW
    0.06
     à
    0.06
    Act Density 0.019%

    No Known Activations