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

    Neuronpedia

    INDEX
    Explanations

    detergent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Almost
    -0.07
     пути
    -0.07
    .pay
    -0.07
     accumulator
    -0.07
     cascade
    -0.06
     almost
    -0.06
    奔
    -0.06
    逃
    -0.06
    争取
    -0.06
     pseudo
    -0.06
    POSITIVE LOGITS
    meal
    0.07
    �
    0.07
     cellul
    0.07
    allis
    0.07
     itching
    0.07
     stringent
    0.07
    呤
    0.06
    링
    0.06
    ıyord
    0.06
    🎞
    0.06
    Act Density 0.003%

    No Known Activations