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

    Neuronpedia

    INDEX
    Explanations

    rates and time intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initialized
    0.83
     rulemaking
    0.79
    Flash
    0.76
    ósfera
    0.73
    urization
    0.73
    Favorite
    0.72
     violators
    0.71
     ব্যবসায়
    0.70
    Runtime
    0.69
    ிற
    0.68
    POSITIVE LOGITS
     dodgy
    1.11
     Whilst
    1.07
    Whilst
    1.04
     trousers
    1.03
     whilst
    1.00
     sociable
    0.96
     xmas
    0.96
     pensioners
    0.95
     pensioner
    0.93
     cheeky
    0.93
    Act Density 0.016%

    No Known Activations