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

    Neuronpedia

    INDEX
    Explanations

    lor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    POWER
    -0.07
    ropped
    -0.06
     film
    -0.06
    MITTED
    -0.06
     organisation
    -0.06
     apenas
    -0.06
     демон
    -0.06
    вод
    -0.06
     safeguards
    -0.06
     交
    -0.06
    POSITIVE LOGITS
    /${
    0.07
    sequently
    0.06
     xy
    0.06
    /'.$
    0.06
     creepy
    0.06
    AndHashCode
    0.06
    	uv
    0.06
    ！",
    0.06
    (if
    0.06
    Benchmark
    0.06
    Act Density 0.012%

    No Known Activations