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

    Neuronpedia

    INDEX
    Explanations

    parameters and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seinem
    0.41
     किंवा
    0.41
     paesi
    0.40
    หรือ
    0.40
    அது
    0.40
    ังสือ
    0.39
     feit
    0.39
     escuelas
    0.39
     disant
    0.39
     njeg
    0.38
    POSITIVE LOGITS
     we
    0.49
     OUTPUT
    0.43
    we
    0.42
    output
    0.41
    Output
    0.41
     prilikom
    0.41
    input
    0.39
    ims
    0.39
     output
    0.38
     reusable
    0.38
    Act Density 0.001%

    No Known Activations