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

    Neuronpedia

    INDEX
    Explanations

    affirmation and confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नसल्या
    0.42
     Unless
    0.39
     लगाएं
    0.38
     Nowhere
    0.38
     نباش
    0.37
     Hardly
    0.36
     없다
    0.36
     Rarely
    0.36
     없이
    0.36
    我们将
    0.36
    POSITIVE LOGITS
    确实
    1.93
     indeed
    1.77
    確實
    1.73
     memang
    1.59
    確かに
    1.48
    indeed
    1.46
     DID
    1.39
    的确
    1.39
    Indeed
    1.36
     DOES
    1.36
    Act Density 0.067%

    No Known Activations