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

    Neuronpedia

    INDEX
    Explanations

    sweep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Light
    -0.07
    (resource
    -0.06
     ad
    -0.06
     firmy
    -0.06
    _Port
    -0.06
    	json
    -0.06
     chmod
    -0.06
    marshall
    -0.06
     сторон
    -0.06
    циклоп
    -0.06
    POSITIVE LOGITS
     sweep
    0.10
     swept
    0.09
     sweeps
    0.08
     suspicions
    0.07
    InputStream
    0.07
     government
    0.07
     marched
    0.06
    擊
    0.06
     assault
    0.06
     moved
    0.06
    Act Density 0.004%

    No Known Activations