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

    Neuronpedia

    INDEX
    Explanations

    listing items with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "**
    1.47
     *"
    1.31
    **,
    1.28
    *",
    1.27
     "*
    1.26
     “[
    1.21
     (**
    1.21
    *"
    1.20
    ****",
    1.20
    ->"
    1.18
    POSITIVE LOGITS
     originalmente
    0.84
     povos
    0.84
     asistir
    0.81
     deren
    0.81
     soltanto
    0.81
     waarvan
    0.79
     agentes
    0.78
     coisas
    0.78
     Ciò
    0.77
     Первая
    0.77
    Act Density 1.618%

    No Known Activations