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

    Neuronpedia

    INDEX
    Explanations

    price fluctuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otten
    0.44
    reson
    0.43
    keits
    0.42
    Kontakt
    0.42
    urni
    0.40
    nacht
    0.40
    produk
    0.40
    isol
    0.38
    डली
    0.38
    vanja
    0.38
    POSITIVE LOGITS
    larını
    0.45
     эсеп
    0.44
     Workplace
    0.43
     Devlet
    0.42
     විශ්
    0.42
     د
    0.40
    кта
    0.40
     фла
    0.40
     Peace
    0.39
     vliegt
    0.39
    Act Density 0.001%

    No Known Activations