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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    太原
    -0.08
    customer
    -0.08
     dare
    -0.07
     bumped
    -0.07
    __.
    -0.07
    (trace
    -0.07
    slide
    -0.07
     starvation
    -0.07
     stratégie
    -0.07
    LiveData
    -0.07
    POSITIVE LOGITS
    ᄋ
    0.06
     involuntary
    0.06
    (container
    0.06
    ⵣ
    0.06
     אחוז
    0.06
     WR
    0.06
    (states
    0.06
     <>
    0.06
     XL
    0.06
    我没有
    0.06
    Act Density 0.090%

    No Known Activations