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

    Neuronpedia

    INDEX
    Explanations

    unusual text formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bitte
    -0.06
    اعدة
    -0.06
     První
    -0.06
    _ctr
    -0.06
    िथ
    -0.06
    廳
    -0.06
     Rox
    -0.06
    іту
    -0.06
    _party
    -0.06
    NAL
    -0.06
    POSITIVE LOGITS
    (login
    0.08
    -Disposition
    0.07
     converted
    0.07
    <head
    0.07
    Chocolate
    0.07
    (Property
    0.07
    (bot
    0.07
     dismal
    0.07
     attempts
    0.07
    ｗ
    0.07
    Act Density 0.000%

    No Known Activations