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

    Neuronpedia

    INDEX
    Explanations

    micro-tasking and surveys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    酩
    0.54
     डाउन
    0.50
    的這個
    0.48
     SIL
    0.48
     SDW
    0.47
    iselt
    0.47
    ἁ
    0.47
    羋
    0.47
    瓠
    0.46
    thema
    0.46
    POSITIVE LOGITS
    }$\
    0.66
    ET
    0.62
     cheque
    0.54
    </code>
    0.54
    টিউ
    0.54
    Unsere
    0.54
    SE
    0.53
    ്ര
    0.52
     timeframe
    0.52
     بيه
    0.52
    Act Density 0.038%

    No Known Activations