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

    Neuronpedia

    INDEX
    Explanations

    adding numbers like 5 and 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chek
    1.16
    𝗼
    1.12
     idade
    1.06
    𝑰
    1.04
    *}\
    1.03
    𝑺
    1.02
     Appart
    1.01
     πραγμα
    1.00
    𝟬
    1.00
     Id
    0.99
    POSITIVE LOGITS
    менение
    1.12
     Balmer
    1.04
    Click
    1.04
     tubercle
    1.03
     treacherous
    1.02
     имеются
    1.00
    외부
    0.98
     gjennom
    0.97
    rollback
    0.95
    smoothed
    0.95
    Act Density 0.001%

    No Known Activations