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

    Neuronpedia

    INDEX
    Explanations

    modal verbs + be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    导致
    0.82
     आपल्याला
    0.78
    導致
    0.75
     menyebabkan
    0.72
     menurunkan
    0.70
    तः
    0.70
     mengurangi
    0.69
     здійсню
    0.69
     curtail
    0.68
     осуществ
    0.67
    POSITIVE LOGITS
     be
    1.16
     being
    1.15
    Being
    1.09
     Being
    1.09
    being
    1.04
     BEING
    1.01
     быть
    0.98
     être
    0.96
     להיות
    0.91
     være
    0.89
    Act Density 0.149%

    No Known Activations