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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     importantes
    0.83
     중요한
    0.75
    꺼
    0.75
     recognize
    0.75
     belangrijk
    0.74
     importants
    0.71
     मिरची
    0.71
    ᱢ
    0.69
     responden
    0.68
     importar
    0.67
    POSITIVE LOGITS
     Overall
    0.79
     overall
    0.77
    全体の
    0.76
     Whole
    0.71
     entire
    0.69
    Reason
    0.68
     தோ
    0.68
    intera
    0.67
     whole
    0.67
     hábito
    0.66
    Act Density 0.306%

    No Known Activations