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

    Neuronpedia

    INDEX
    Explanations

    advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    假
    -0.07
    備
    -0.06
     Tories
    -0.06
    728
    -0.06
     tespit
    -0.06
    omanip
    -0.06
     libido
    -0.06
     pancreatic
    -0.06
    LEY
    -0.06
    owo
    -0.06
    POSITIVE LOGITS
    /{
    0.07
    ştir
    0.07
    /events
    0.07
    itian
    0.07
    ność
    0.06
    withstanding
    0.06
    ें।
    0.06
     millions
    0.06
    arser
    0.06
    řet
    0.06
    Act Density 0.040%

    No Known Activations