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

    Neuronpedia

    INDEX
    Explanations

    portfolio and creative fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     storytelling
    0.45
     священ
    0.45
     énon
    0.45
     partage
    0.42
     $€
    0.41
    长老
    0.41
    差点
    0.39
     olhar
    0.39
    bedkar
    0.39
    Interpret
    0.38
    POSITIVE LOGITS
     thereof
    0.48
    而非
    0.47
     BUT
    0.44
     coupler
    0.44
    carrier
    0.42
    봉
    0.42
    但是
    0.42
     but
    0.41
    부가
    0.41
     পৃথিবীর
    0.40
    Act Density 0.012%

    No Known Activations