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

    Neuronpedia

    INDEX
    Explanations

    substitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discerning
    1.94
    दान
    1.82
    icht
    1.72
    ä
    1.68
    yii
    1.68
    মাণ
    1.67
    𝘦
    1.66
    GameObject
    1.64
    вості
    1.61
    shrink
    1.59
    POSITIVE LOGITS
    uing
    1.55
    anneled
    1.47
    る
    1.46
     мира
    1.46
    徊
    1.45
    ल्पनिक
    1.44
     Subsequently
    1.42
    Cuánt
    1.42
     subsequently
    1.41
    ྜ
    1.39
    Act Density 0.000%

    No Known Activations