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

    Neuronpedia

    INDEX
    Explanations

    say "a word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    电商
    -0.08
    看不见
    -0.07
    激活
    -0.07
    and
    -0.07
    -trans
    -0.07
     database
    -0.07
     Odyssey
    -0.07
    踩
    -0.07
     Prior
    -0.07
     reverse
    -0.07
    POSITIVE LOGITS
     HtmlWebpackPlugin
    0.07
    SequentialGroup
    0.07
    냑
    0.07
     velvet
    0.06
    WAY
    0.06
    ruta
    0.06
     luxurious
    0.06
    dress
    0.06
    STONE
    0.06
    *:
    0.06
    Act Density 0.000%

    No Known Activations