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

    Neuronpedia

    INDEX
    Explanations

    code or technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     การแข
    -0.06
     Integr
    -0.06
     Philip
    -0.06
     hazard
    -0.06
     isChecked
    -0.06
    attered
    -0.06
    فع
    -0.06
     tracking
    -0.06
    (configuration
    -0.06
     Toilet
    -0.06
    POSITIVE LOGITS
    ，比
    0.07
     美
    0.07
    跌
    0.06
    WITHOUT
    0.06
    óg
    0.06
     مثل
    0.06
    rium
    0.06
    些
    0.06
     آم
    0.06
     beast
    0.06
    Act Density 0.000%

    No Known Activations