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

    Neuronpedia

    INDEX
    Explanations

    parenthesis and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ours
    -0.07
     plat
    -0.06
     UB
    -0.06
    loaded
    -0.06
    غان
    -0.06
     adverts
    -0.06
     yaw
    -0.06
     Crushing
    -0.06
     chứa
    -0.06
    POSITIVE LOGITS
     강
    0.08
    ~↵
    0.07
     교수
    0.07
    (""+
    0.07
    rå
    0.06
    委員
    0.06
     tonight
    0.06
    _sync
    0.06
    vtk
    0.06
     цьому
    0.06
    Act Density 0.027%

    No Known Activations