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

    Neuronpedia

    INDEX
    Explanations

    extends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (reordered
    -0.07
     Stops
    -0.07
    \"",
    -0.07
     MUSIC
    -0.07
    �
    -0.07
     końcu
    -0.07
    فئ
    -0.07
    (rp
    -0.06
    波动
    -0.06
    UART
    -0.06
    POSITIVE LOGITS
     Mart
    0.07
     aliqu
    0.07
    exampleInputEmail
    0.06
     barbar
    0.06
     antique
    0.06
    directory
    0.06
    蓠
    0.06
     should
    0.06
     Heal
    0.06
     leather
    0.06
    Act Density 0.004%

    No Known Activations