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

    Neuronpedia

    INDEX
    Explanations

    XL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Babe
    -0.07
    (encoder
    -0.07
    utra
    -0.07
    のも
    -0.07
     cảm
    -0.07
     баб
    -0.07
     göre
    -0.07
    ама
    -0.07
    Pay
    -0.06
     객
    -0.06
    POSITIVE LOGITS
     advantageous
    0.06
    <Animator
    0.06
    =center
    0.06
    丁
    0.06
     sexo
    0.05
     divides
    0.05
     Las
    0.05
     lofty
    0.05
     skilled
    0.05
     předmět
    0.05
    Act Density 0.001%

    No Known Activations