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

    Neuronpedia

    INDEX
    Explanations

    Text format and content generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sogen
    -0.09
     Sheng
    -0.09
    зв
    -0.08
     sta
    -0.08
     sometime
    -0.08
     же
    -0.07
     siyang
    -0.07
     viktig
    -0.07
     люб
    -0.07
     вист
    -0.07
    POSITIVE LOGITS
     nor
    0.22
     anymore
    0.19
     سوى
    0.17
     hoeft
    0.15
     ούτε
    0.15
     necessarily
    0.15
    nor
    0.15
     ningún
    0.15
     hoeven
    0.15
     enää
    0.15
    Act Density 2.168%

    No Known Activations