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

    Neuronpedia

    INDEX
    Explanations

    add or + and increment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mundo
    1.32
    edar
    1.32
     այդ
    1.27
    weile
    1.26
    ulfide
    1.17
    mechanism
    1.17
    Pedido
    1.17
     salesperson
    1.14
    द्वितीय
    1.14
     secretory
    1.13
    POSITIVE LOGITS
     Dzięki
    1.07
     gana
    1.01
    以
    1.00
    uent
    0.97
    uration
    0.94
    TERS
    0.93
     Lect
    0.88
    ರವಾಗಿ
    0.87
     Erasmus
    0.86
    വന്‍
    0.86
    Act Density 0.004%

    No Known Activations