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

    Neuronpedia

    INDEX
    Explanations

    regression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     results
    -0.07
     Graphic
    -0.07
     judicial
    -0.07
     Toe
    -0.06
     iter
    -0.06
     presents
    -0.06
    �
    -0.06
     TP
    -0.06
     Twist
    -0.06
    iała
    -0.06
    POSITIVE LOGITS
    ोन
    0.06
    台
    0.06
    ("#{
    0.06
     handleMessage
    0.06
    ‌پدی
    0.06
    ObjectName
    0.06
    .Execution
    0.06
     Kohana
    0.06
     RemoteException
    0.06
     नय
    0.06
    Act Density 0.005%

    No Known Activations