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

    Neuronpedia

    INDEX
    Explanations

    .S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GAN
    -0.07
    ạn
    -0.07
     bathroom
    -0.07
    נוח
    -0.07
    手动
    -0.06
     chasing
    -0.06
     Depending
    -0.06
     laundry
    -0.06
    wä
    -0.06
    Toggle
    -0.06
    POSITIVE LOGITS
    绌
    0.08
     bees
    0.08
    PLL
    0.07
    رهاب
    0.07
     retrofit
    0.07
    ┻
    0.07
    �
    0.07
     الإرهاب
    0.07
    إرهاب
    0.07
     velit
    0.07
    Act Density 0.001%

    No Known Activations