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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xB9>
    0.47
    ницей
    0.43
    ்ச்ச
    0.40
    ยม
    0.39
    ্বর
    0.38
    женный
    0.38
    ница
    0.38
    韮
    0.38
    क्रोस
    0.38
    anzia
    0.38
    POSITIVE LOGITS
    7
    0.68
    6
    0.61
     ७
    0.54
     seventh
    0.50
     ৭
    0.50
    ７
    0.49
     seventy
    0.49
    ७
    0.47
     sixty
    0.47
     Sixty
    0.47
    Act Density 0.012%

    No Known Activations