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

    Neuronpedia

    INDEX
    Explanations

    states, conditions, or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     др
    0.50
     אך
    0.46
    வரின்
    0.46
     하며
    0.46
     ін
    0.44
     stets
    0.43
     باقي
    0.43
     Meski
    0.43
     বঙ্গের
    0.42
    により
    0.41
    POSITIVE LOGITS
     ahorita
    0.86
     ähm
    0.80
     굉장히
    0.76
     tutaj
    0.73
     uh
    0.70
     poquito
    0.70
     Yeah
    0.68
    っていう
    0.67
    比如说
    0.66
    或者是
    0.64
    Act Density 0.024%

    No Known Activations