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

    Neuronpedia

    INDEX
    Explanations

    want to be clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تريد
    0.50
     хотите
    0.49
     particuliers
    0.41
     желания
    0.41
     membut
    0.41
     смотрите
    0.41
     scoprire
    0.39
     يريد
    0.39
     schemes
    0.38
     مز
    0.38
    POSITIVE LOGITS
     offer
    0.71
     remind
    0.69
     clarify
    0.67
     reiterate
    0.66
     reaffirm
    0.64
     caution
    0.64
     responded
    0.64
     clarified
    0.62
    Offer
    0.62
     menawarkan
    0.62
    Act Density 0.009%

    No Known Activations