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

    Neuronpedia

    INDEX
    Explanations

    list items and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.80
     latter
    0.75
     বলেও
    0.71
     moreover
    0.71
     or
    0.70
     other
    0.68
     second
    0.67
     another
    0.66
     others
    0.66
    或是
    0.65
    POSITIVE LOGITS
       
    1.55
    1.43
    1.41
    •
    1.40
     •
    1.39
     ・
    1.29
    *
    1.24
        
    1.23
     ▪
    1.23
    ➢
    1.21
    Act Density 2.657%

    No Known Activations