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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     }
↵
↵
↵
    -0.07
    [from
    -0.07
     SEX
    -0.07
    	FROM
    -0.07
    _SEG
    -0.07
    ORMAL
    -0.07
    beh
    -0.07
    -self
    -0.07
     ?></
    -0.07
    	df
    -0.07
    POSITIVE LOGITS
    кладыва
    0.07
     absorbing
    0.07
    пуска
    0.07
     cautiously
    0.07
     russian
    0.07
    ảo
    0.07
    原谅
    0.07
    楽しめる
    0.07
     arty
    0.07
    ij
    0.07
    Act Density 0.082%

    No Known Activations