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

    Neuronpedia

    INDEX
    Explanations

    ate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grenades
    -0.07
     smrti
    -0.06
     Zinc
    -0.06
     supplies
    -0.06
     ster
    -0.06
     induces
    -0.06
     tempo
    -0.06
    Very
    -0.06
     GREAT
    -0.06
    istema
    -0.06
    POSITIVE LOGITS
    国際
    0.07
     Shine
    0.06
     raced
    0.06
     کیلومتر
    0.06
    run
    0.06
    ville
    0.06
    械
    0.06
    روج
    0.06
    俗
    0.06
    _sheet
    0.06
    Act Density 0.004%

    No Known Activations