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

    Neuronpedia

    INDEX
    Explanations

    enthusiastic greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क्ट
    0.42
    และการ
    0.41
    рел
    0.40
    Marcus
    0.40
    र्नर
    0.40
    สิน
    0.40
    номет
    0.39
    рти
    0.38
     والخ
    0.38
    тельстве
    0.38
    POSITIVE LOGITS
     Ensemble
    0.44
     Maybe
    0.43
     Perhaps
    0.43
     Rac
    0.41
     Muito
    0.41
     Pepper
    0.41
     ♥
    0.41
     ἢ
    0.40
     Could
    0.39
    してみてください
    0.39
    Act Density 0.015%

    No Known Activations