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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ný
    -0.07
    5
    -0.06
     Trib
    -0.06
     hé
    -0.06
    ESA
    -0.06
     ;
↵
    -0.06
     prav
    -0.06
    Statistics
    -0.06
    ная
    -0.06
    763
    -0.06
    POSITIVE LOGITS
     كم
    0.08
    既然
    0.07
    .squareup
    0.07
    .Safe
    0.07
    	alpha
    0.06
     IOError
    0.06
     artifact
    0.06
    .Mapper
    0.06
     lucky
    0.06
    Boot
    0.06
    Act Density 0.007%

    No Known Activations