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

    Neuronpedia

    INDEX
    Explanations

    unite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     “[
    -0.07
     příliš
    -0.07
     astronomical
    -0.06
     чувств
    -0.06
    .openg
    -0.06
     Excell
    -0.06
     comes
    -0.06
     unavoid
    -0.06
    stackoverflow
    -0.06
     Airbnb
    -0.06
    POSITIVE LOGITS
     unite
    0.08
     unified
    0.07
     updating
    0.07
     الاتحاد
    0.07
    _packet
    0.07
    igest
    0.07
     ERC
    0.07
    �
    0.07
    INO
    0.07
    ेट
    0.07
    Act Density 0.015%

    No Known Activations