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

    Neuronpedia

    INDEX
    Explanations

    helper functions and time updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adriatic
    0.61
     misfortunes
    0.49
     murders
    0.48
     reds
    0.48
     Levante
    0.47
     ammon
    0.46
     Sumatra
    0.45
     crux
    0.45
     jungles
    0.45
     carnage
    0.44
    POSITIVE LOGITS
     ඇ
    0.44
     ሂደት
    0.43
    Pat
    0.42
    STE
    0.42
    Smoke
    0.41
    ILLE
    0.40
    e
    0.40
    chodzi
    0.39
     probed
    0.39
    ivez
    0.39
    Act Density 0.005%

    No Known Activations