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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     laurea
    1.17
    по
    1.16
    Freq
    1.15
    ⌈
    1.14
    t
    1.11
    tble
    1.10
    бе
    1.10
     المياه
    1.09
    gre
    1.07
    𝑎
    1.07
    POSITIVE LOGITS
    PDP
    1.29
    ᙱ
    1.07
     shocks
    1.06
    дцать
    1.05
     preach
    1.03
    杠
    1.03
     improvised
    1.02
     territor
    1.02
    杲
    1.01
    visory
    1.00
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.