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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    that
    0.28
    га
    0.27
     સમયે
    0.27
    т
    0.26
    ваясь
    0.26
    ната
    0.26
    ለያዩ
    0.26
     informacion
    0.26
    что
    0.26
    су
    0.25
    POSITIVE LOGITS
    in
    0.32
     to
    0.32
    /
    0.29
    -
    0.29
    ]
    0.28
    \
    0.27
    inia
    0.26
     &
    0.26
    ↵↵
    0.25
    ;
    0.24
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.