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

    Neuronpedia

    INDEX
    Explanations

    Time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dynamics
    -0.07
    도
    -0.07
    (customer
    -0.07
    'im
    -0.06
     camps
    -0.06
     tương
    -0.06
     customary
    -0.06
     dub
    -0.06
    iton
    -0.06
     optimistic
    -0.06
    POSITIVE LOGITS
    .stream
    0.06
    ziel
    0.06
    asename
    0.06
     Stall
    0.06
     carbohydrate
    0.06
    _rewards
    0.06
    vented
    0.06
     Passed
    0.06
    .bootstrapcdn
    0.06
    UNICATION
    0.06
    Act Density 0.138%

    No Known Activations