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

    Neuronpedia

    INDEX
    Explanations

    people you don't know well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Რ
    1.08
    Ე
    1.04
    Ს
    1.00
     Kräfte
    1.00
    DrvGPIO
    0.99
    ībā
    0.99
    āna
    0.97
    न्व
    0.95
    арма
    0.94
    Კ
    0.93
    POSITIVE LOGITS
     hoặc
    1.22
     til
    1.20
     lol
    1.20
     newest
    1.19
     or
    1.19
     atau
    1.14
     किसी
    1.13
     flowers
    1.12
     friends
    1.11
     bonuses
    1.11
    Act Density 0.002%

    No Known Activations