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

    Neuronpedia

    INDEX
    Explanations

    dressing, dresses, drain, spritzer, refresh, rinse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mieszkań
    0.85
     setempat
    0.84
     menyampaikan
    0.73
    もちろん
    0.70
     memastikan
    0.70
    ։
    0.68
     estamos
    0.64
     όλα
    0.64
    ließlich
    0.63
     predictors
    0.63
    POSITIVE LOGITS
    e
    0.79
     или
    0.79
     or
    0.75
    或
    0.73
    s
    0.70
     या
    0.69
    이나
    0.68
    或者
    0.66
     ಅಥವಾ
    0.66
     veya
    0.66
    Act Density 0.000%

    No Known Activations