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

    Neuronpedia

    INDEX
    Explanations

    launch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensitivity
    -0.08
     Pé
    -0.08
    ᥔ
    -0.07
    ביטוח
    -0.07
    CustomerId
    -0.07
    ViewModel
    -0.07
    ດ
    -0.07
    婞
    -0.07
    报废
    -0.07
     revenge
    -0.07
    POSITIVE LOGITS
     launch
    0.07
     throw
    0.07
     launched
    0.07
    (plugin
    0.07
     chilled
    0.07
     trailer
    0.06
    usband
    0.06
     glanced
    0.06
     ank
    0.06
    鲩
    0.06
    Act Density 0.009%

    No Known Activations