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

    Neuronpedia

    INDEX
    Explanations

    a to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Uno
    0.46
    rops
    0.44
     мора
    0.42
    о
    0.42
    Das
    0.42
    UNO
    0.41
    Bro
    0.41
    рано
    0.41
    рито
    0.40
    Adri
    0.40
    POSITIVE LOGITS
     konsep
    0.44
     لیست
    0.43
     resellers
    0.43
     SoaException
    0.43
     الواي
    0.42
     hyperlocal
    0.42
     വൈദ്യുതി
    0.41
    券
    0.41
     suburbs
    0.41
     एक्सच
    0.41
    Act Density 0.001%

    No Known Activations