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

    Neuronpedia

    INDEX
    Explanations

    的 noun/concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     again
    0.74
    ?
    0.64
    again
    0.62
     Again
    0.60
    Again
    0.57
    又
    0.57
     igen
    0.55
     novamente
    0.54
     மீண்டும்
    0.52
     igjen
    0.51
    POSITIVE LOGITS
    癀
    0.54
    痳
    0.54
     टीच
    0.50
    𒄷
    0.49
     বিষয়ে
    0.48
     соци
    0.48
    雱
    0.48
     пирами
    0.48
     люди
    0.46
     уены
    0.46
    Act Density 0.001%

    No Known Activations