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

    Neuronpedia

    INDEX
    Explanations

    verb present tense forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ล
    0.82
     Including
    0.76
    術
    0.74
    atics
    0.74
    itics
    0.74
     Lending
    0.70
    ിയി
    0.69
     کول
    0.69
    FXML
    0.68
     Boc
    0.68
    POSITIVE LOGITS
     waarom
    0.77
     વખતે
    0.77
     move
    0.75
     escucha
    0.75
    hes
    0.75
    ુંદર
    0.74
    pra
    0.72
    UTCDate
    0.71
     हैं
    0.70
     voici
    0.69
    Act Density 0.004%

    No Known Activations