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

    Neuronpedia

    INDEX
    Explanations

    to give advice or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بنائیں
    0.81
     করবে
    0.79
     त्यांना
    0.77
    тувати
    0.77
     manteniendo
    0.76
    жити
    0.75
     करेगा
    0.75
     leva
    0.74
    чала
    0.73
     করছেন
    0.73
    POSITIVE LOGITS
     ser
    0.85
     existir
    0.77
    Ser
    0.71
    ser
    0.70
    aber
    0.69
    nder
    0.68
     haver
    0.67
     dar
    0.66
     Verse
    0.66
    aver
    0.65
    Act Density 0.130%

    No Known Activations