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

    Neuronpedia

    INDEX
    Explanations

    votes above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.59
    (
    0.50
    踏
    0.47
    с
    0.46
    ;
    0.45
     compaction
    0.45
     inhal
    0.44
    :
    0.44
     Haar
    0.43
     dreamy
    0.43
    POSITIVE LOGITS
    ኛውም
    0.49
     वेळी
    0.47
    碉
    0.46
     შორის
    0.45
    वरील
    0.45
     দূতাব
    0.45
     بیاکت
    0.45
    樑
    0.45
    RxDocument
    0.45
     لنا
    0.44
    Act Density 0.002%

    No Known Activations