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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pq
    1.17
    tw
    1.15
    pang
    1.07
    ancer
    1.05
    vironment
    1.05
    clazz
    1.03
    wiąz
    1.02
    닙
    1.00
    gd
    1.00
    ledning
    0.99
    POSITIVE LOGITS
     Як
    1.28
    ஸ்
    1.16
     किशोर
    1.14
    ும்
    1.13
    𝘥
    1.12
    𝘴
    1.12
     Тео
    1.10
    𝘺
    1.07
    uları
    1.07
     Nus
    1.06
    Act Density 0.000%

    No Known Activations