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

    Neuronpedia

    INDEX
    Explanations

    your name or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ضاع
    0.40
     analges
    0.35
     Macon
    0.35
     ferries
    0.34
     grazing
    0.34
     ‘
    0.34
     afternoons
    0.34
     ’
    0.33
     batches
    0.33
     Westfield
    0.33
    POSITIVE LOGITS
     neki
    0.52
    名稱
    0.49
     например
    0.47
     مثلا
    0.47
    your
    0.46
     exempel
    0.46
     mesela
    0.46
    name
    0.45
     Например
    0.45
    esempio
    0.45
    Act Density 0.254%

    No Known Activations