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

    Neuronpedia

    INDEX
    Explanations

    Complex sentence structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    berg
    -0.07
    ذار
    -0.06
    논
    -0.06
     Ingredients
    -0.06
     Tac
    -0.06
     Equip
    -0.06
    \Repositories
    -0.06
    calls
    -0.06
     Nude
    -0.06
     Killer
    -0.06
    POSITIVE LOGITS
    (Me
    0.07
    (map
    0.06
     sword
    0.06
    (pb
    0.06
     hệ
    0.06
    Met
    0.06
    dataset
    0.06
     psychic
    0.06
    (axis
    0.06
    ออนไลน
    0.06
    Act Density 0.057%

    No Known Activations