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

    Neuronpedia

    INDEX
    Explanations

    predicting text continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اد
    0.53
    성
    0.46
    桷
    0.45
    nous
    0.45
     Headquarters
    0.44
     personajes
    0.43
    삼
    0.42
    クエスト
    0.42
    informations
    0.42
    characters
    0.41
    POSITIVE LOGITS
     advertised
    0.52
    uti
    0.50
     selectivity
    0.48
    hede
    0.47
    ographic
    0.47
    ,,
    0.46
     cui
    0.46
    uiti
    0.46
     tathapi
    0.46
     MVC
    0.46
    Act Density 0.001%

    No Known Activations