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

    Neuronpedia

    INDEX
    Explanations

    links to Wikipedia articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Basil
    0.44
     তখনকার
    0.44
     pede
    0.41
     old
    0.41
     unui
    0.41
     وقتی
    0.40
     ghostly
    0.39
     stately
    0.39
     fanciful
    0.39
     If
    0.39
    POSITIVE LOGITS
    令和
    0.61
    ₺
    0.57
     metaverse
    0.54
     ২০২৩
    0.54
    ₿
    0.51
    ২০
    0.50
    🥳
    0.50
    https
    0.49
    ​​​​
    0.49
     официально
    0.49
    Act Density 0.035%

    No Known Activations