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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    нибудь
    1.15
     ragazzo
    1.12
    𝚓
    1.12
    okovic
    1.10
     delanter
    1.08
     felices
    1.07
    EnglishMarks
    1.07
     runter
    1.06
     proyek
    1.05
     voulais
    1.05
    POSITIVE LOGITS
     in
    1.16
     In
    1.09
    :
    1.03
     Epidemi
    1.02
     for
    1.00
    ;
    0.96
     at
    0.95
     Importance
    0.94
     both
    0.94
     February
    0.94
    Act Density 0.634%

    No Known Activations