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

    Neuronpedia

    INDEX
    Explanations

    Otherwise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IALIZ
    -0.07
     six
    -0.07
    795
    -0.06
     cluster
    -0.06
    12
    -0.06
     Joan
    -0.06
     ThreadPool
    -0.06
    348
    -0.06
    826
    -0.06
    	num
    -0.06
    POSITIVE LOGITS
     otherwise
    0.09
     Otherwise
    0.08
    Otherwise
    0.08
    撃
    0.08
    شه
    0.07
    ):(
    0.07
     unintention
    0.07
     warning
    0.07
    ready
    0.06
     вив
    0.06
    Act Density 0.006%

    No Known Activations