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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     державного
    -0.06
    ерв
    -0.06
     drastically
    -0.06
    addOn
    -0.06
    .State
    -0.06
     одна
    -0.05
     prevalence
    -0.05
    /{
    -0.05
    avax
    -0.05
    nw
    -0.05
    POSITIVE LOGITS
    .label
    0.07
     kay
    0.07
    akin
    0.07
     tarihli
    0.06
    FULL
    0.06
    uyến
    0.06
    attering
    0.06
     Tee
    0.06
    .Channel
    0.06
    ΕΣ
    0.06
    Act Density 0.002%

    No Known Activations