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

    Neuronpedia

    INDEX
    Explanations

    Even if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ft
    0.52
    å
    0.51
    :
    0.45
    \.
    0.44
    of
    0.43
    е
    0.43
     komunikasi
    0.43
     RIS
    0.43
    fehlung
    0.42
     पिछली
    0.42
    POSITIVE LOGITS
    multilayer
    0.47
    GORITHM
    0.47
     infringer
    0.47
     averse
    0.45
     unsurpassed
    0.45
    િંગ
    0.45
    iénd
    0.44
    UILLER
    0.43
    marshalN
    0.43
     unforgettable
    0.43
    Act Density 0.000%

    No Known Activations