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

    Neuronpedia

    INDEX
    Explanations

    less intimidating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ട്ടുണ്ട്
    0.43
     PubMed
    0.42
    Wait
    0.42
    कट
    0.42
     umbrellas
    0.41
     ruffled
    0.41
     NVIC
    0.41
     MCT
    0.41
    Exception
    0.40
     refunds
    0.39
    POSITIVE LOGITS
     phi
    0.44
     ذره
    0.44
     சேர்த்து
    0.44
     capa
    0.43
     füh
    0.43
     vei
    0.42
     Petr
    0.40
    抒
    0.40
     wesentlich
    0.40
    enti
    0.40
    Act Density 0.011%

    No Known Activations