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

    Neuronpedia

    INDEX
    Explanations

    Nonsense text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Report
    -0.07
     flora
    -0.07
    面的
    -0.07
     lm
    -0.06
    standing
    -0.06
     arrogance
    -0.06
     allocation
    -0.06
    )">↵
    -0.06
     safe
    -0.06
    :
↵
    -0.06
    POSITIVE LOGITS
     StreamLazy
    0.06
    -develop
    0.06
    ackBar
    0.06
    THON
    0.06
     Decomp
    0.06
     Charl
    0.06
     Scene
    0.06
     حک
    0.06
     jednotlivých
    0.06
    modx
    0.06
    Act Density 0.011%

    No Known Activations