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

    Neuronpedia

    INDEX
    Explanations

    proven ability and successful results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    とりあえず
    0.52
    到时候
    0.51
     eventuali
    0.50
     약간
    0.48
     intentar
    0.48
     tiredness
    0.48
     trochu
    0.47
     tries
    0.47
     storing
    0.46
     기본적인
    0.46
    POSITIVE LOGITS
     успешно
    0.88
     successfully
    0.85
    successfully
    0.83
     multimillion
    0.72
     succesfully
    0.71
     erfolgreich
    0.70
    Successfully
    0.70
     Successfully
    0.68
     SUCCESSFULLY
    0.67
     सफलतापूर्वक
    0.66
    Act Density 0.029%

    No Known Activations