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

    Neuronpedia

    INDEX
    Explanations

    conservation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lu
    -0.07
     ern
    -0.07
    _off
    -0.06
    562
    -0.06
    ฤษ
    -0.06
    ζί
    -0.06
    scss
    -0.06
    _plan
    -0.06
     руб
    -0.06
    立刻
    -0.06
    POSITIVE LOGITS
     vouchers
    0.07
     Hungary
    0.07
     conference
    0.07
    シア
    0.06
     solution
    0.06
     devant
    0.06
    (fill
    0.06
     νεφοκάλυψης
    0.06
    Height
    0.06
    veled
    0.06
    Act Density 0.017%

    No Known Activations