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

    Neuronpedia

    INDEX
    Explanations

    select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ിത്ത
    -0.08
     দ
    -0.08
     ਦਾ
    -0.07
     Collective
    -0.07
     ভুল
    -0.07
    ദ്യ
    -0.07
    .Endpoint
    -0.07
     וצ
    -0.07
     chores
    -0.07
     ਦੇ
    -0.07
    POSITIVE LOGITS
    assigned
    0.08
     DAN
    0.07
     metast
    0.07
     transistor
    0.07
     broadcast
    0.07
     GMT
    0.07
     mobiles
    0.07
     ign
    0.07
     assigned
    0.07
     product
    0.07
    Act Density 0.003%

    No Known Activations