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

    Neuronpedia

    INDEX
    Explanations

    you are / you can / i will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palatable
    0.70
     blurring
    0.67
     avoiding
    0.67
     hefty
    0.65
     prevalent
    0.65
     rife
    0.65
     viable
    0.65
     accruing
    0.62
     streaming
    0.62
     skirting
    0.62
    POSITIVE LOGITS
     wrote
    1.09
     forgot
    1.05
     نے
    1.04
     chose
    1.04
     want
    0.99
     took
    0.98
     owns
    0.98
     gave
    0.98
     will
    0.96
     telah
    0.95
    Act Density 0.468%

    No Known Activations