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

    Neuronpedia

    INDEX
    Explanations

    defining questions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     статисти
    0.48
    ״
    0.47
    м
    0.46
    ехал
    0.45
    ת
    0.44
    畂
    0.44
     ಸಹಾಯ
    0.43
     seinem
    0.43
     ಸಮಯದಲ್ಲಿ
    0.43
     MQTT
    0.42
    POSITIVE LOGITS
     &
    0.54
    oconut
    0.42
     ,
    0.42
     Coconut
    0.41
    mselves
    0.40
    ounce
    0.39
    orough
    0.38
     Yoga
    0.38
    oodle
    0.38
     Porcelain
    0.38
    Act Density 0.026%

    No Known Activations