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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plaza
    -0.07
    Roman
    -0.06
     Kawasaki
    -0.06
    ));//
    -0.06
    ifferential
    -0.06
     Please
    -0.06
    Radio
    -0.06
    iazza
    -0.06
    方面
    -0.06
    -tank
    -0.06
    POSITIVE LOGITS
    ет
    0.07
     教
    0.06
    .Up
    0.06
     обязан
    0.06
     �
    0.06
     EAR
    0.06
     Hear
    0.06
    InvalidArgumentException
    0.06
     textbook
    0.06
     داد
    0.06
    Act Density 0.014%

    No Known Activations