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

    Neuronpedia

    INDEX
    Explanations

    goods, device, along, soot, blaming, activations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শিল্পী
    0.52
     pinMode
    0.52
    も含
    0.52
    ទំនាក់
    0.50
    <unused57>
    0.50
     ჩატი
    0.50
     ሂ
    0.50
     elevationMap
    0.49
     공부해
    0.49
    ဖို့
    0.48
    POSITIVE LOGITS
    od
    0.50
    nes
    0.49
     on
    0.45
    itions
    0.45
    \
    0.45
     It
    0.45
     je
    0.45
    0
    0.44
    ._
    0.43
    ↵↵
    0.43
    Act Density 0.000%

    No Known Activations