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

    Neuronpedia

    INDEX
    Explanations

    named

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     到
    -0.08
     spooky
    -0.07
     tea
    -0.07
     berry
    -0.07
     Эти
    -0.07
    .credentials
    -0.06
     because
    -0.06
     Mayo
    -0.06
     isnt
    -0.06
     populated
    -0.06
    POSITIVE LOGITS
     HttpResponseMessage
    0.06
    ABCDEFGHI
    0.06
    .setDescription
    0.06
     sme
    0.06
    .cloudflare
    0.06
    イル
    0.06
     金
    0.06
    ORIZ
    0.05
    plt
    0.05
    .prop
    0.05
    Act Density 0.015%

    No Known Activations