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

    Neuronpedia

    INDEX
    Explanations

    Informal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devil
    -0.07
    _UTILS
    -0.07
    _odd
    -0.06
     pan
    -0.06
     CPC
    -0.06
     pong
    -0.06
     probs
    -0.06
    CHE
    -0.06
     гип
    -0.06
    .pth
    -0.06
    POSITIVE LOGITS
    	atomic
    0.07
    ранения
    0.07
    وزيع
    0.06
     Sinclair
    0.06
    ordered
    0.06
    ?"
    0.06
     structure
    0.06
     EntryPoint
    0.06
    -Jan
    0.06
    /order
    0.06
    Act Density 0.016%

    No Known Activations