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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ორგანო
    0.64
     authorise
    0.54
    农民
    0.54
     paysans
    0.53
    瓤
    0.52
    gmzy
    0.51
    <unused442>
    0.50
    <unused287>
    0.49
    erçe
    0.49
    केमॉन
    0.48
    POSITIVE LOGITS
     slightly
    0.61
    0.52
     Slightly
    0.51
     slight
    0.47
     &
    0.46
     nearly
    0.46
     almost
    0.45
     mid
    0.45
     second
    0.45
    slightly
    0.45
    Act Density 0.061%

    No Known Activations