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

    Neuronpedia

    INDEX
    Explanations

    Countries and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    छ
    -0.08
     छ
    -0.08
     manche
    -0.07
    258
    -0.07
    -assisted
    -0.07
     ascertain
    -0.07
     исти
    -0.07
    ψε
    -0.07
     صحي
    -0.07
     सामान
    -0.07
    POSITIVE LOGITS
    是一
    0.10
     boasts
    0.09
     notoriously
    0.08
     famously
    0.08
     totiž
    0.08
     decept
    0.08
     обладает
    0.08
    ika
    0.08
     prides
    0.08
     Foundation
    0.08
    Act Density 0.110%

    No Known Activations