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

    Neuronpedia

    INDEX
    Explanations

    importance or necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pector
    0.44
     हमने
    0.43
     habían
    0.43
     _,
    0.43
     affiche
    0.42
     telah
    0.41
    トル
    0.40
     habíamos
    0.40
     troviamo
    0.40
    ophila
    0.40
    POSITIVE LOGITS
    ควร
    0.71
     поможет
    0.70
     должна
    0.69
    你应该
    0.69
     должны
    0.66
     якщо
    0.64
     должен
    0.62
     يجب
    0.62
     ваша
    0.61
     нужно
    0.61
    Act Density 0.356%

    No Known Activations