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

    Neuronpedia

    INDEX
    Explanations

    recently popular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Yes
    1.03
    Sign
    0.94
    Click
    0.91
    YES
    0.90
    Okay
    0.89
    0.85
    Submitted
    0.84
    Please
    0.84
    Date
    0.84
    OK
    0.82
    POSITIVE LOGITS
     Ace
    1.18
     popular
    1.13
     ace
    1.07
     recently
    1.05
     lately
    1.05
     populaire
    1.01
    ace
    0.99
     recent
    0.97
     ….
    0.96
    0.96
    Act Density 0.003%

    No Known Activations