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

    Neuronpedia

    INDEX
    Explanations

    straighten teeth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ancient
    0.47
    ܟ
    0.44
     Sumber
    0.44
     hexadecimal
    0.43
    ANTE
    0.42
     inches
    0.42
     Andere
    0.42
    څ
    0.42
     Hongkong
    0.42
     asynchronous
    0.41
    POSITIVE LOGITS
    च्छेद
    0.45
    orientation
    0.42
    苦手
    0.40
    沬
    0.40
    eword
    0.40
     θέση
    0.40
     ઘટા
    0.40
    ❐
    0.39
     overshoot
    0.39
     ভারসাম্য
    0.39
    Act Density 0.008%

    No Known Activations