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

    Neuronpedia

    INDEX
    Explanations

    Talking/imperative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drops
    -0.07
    fleet
    -0.06
     Abyss
    -0.06
     prescription
    -0.06
    alarını
    -0.06
    �
    -0.06
     openings
    -0.06
    criptions
    -0.06
    aghan
    -0.06
     progression
    -0.06
    POSITIVE LOGITS
    (quantity
    0.07
    .*;↵
    0.06
     نع
    0.06
    (var
    0.06
    坊
    0.06
    AAP
    0.06
    ssize
    0.06
     Xiaomi
    0.06
    ilename
    0.06
     �
    0.06
    Act Density 0.097%

    No Known Activations