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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MyLocation
    0.42
    Bubble
    0.40
     уника
    0.40
    larımız
    0.40
     वक़्त
    0.39
    Amazing
    0.39
    ッセージ
    0.39
    mkdir
    0.38
    <0xE2>
    0.38
    Hemos
    0.38
    POSITIVE LOGITS
     (
    0.45
    acre
    0.43
     seems
    0.41
     Fuller
    0.41
     seem
    0.40
     comprised
    0.39
     daughter
    0.39
     och
    0.39
    ?)
    0.38
     now
    0.38
    Act Density 0.001%

    No Known Activations