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

    Neuronpedia

    INDEX
    Explanations

    commitment to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обеща
    0.73
    promise
    0.70
     promise
    0.70
     Promised
    0.66
     promised
    0.66
     Promise
    0.63
     وعد
    0.61
     promises
    0.60
    promises
    0.58
     promesa
    0.57
    POSITIVE LOGITS
     ধারা
    0.44
     зро
    0.43
     crimes
    0.43
     comm
    0.42
     commas
    0.41
    lerden
    0.41
     hydrate
    0.40
     awkward
    0.40
     hydrated
    0.40
     perjalanan
    0.40
    Act Density 0.004%

    No Known Activations