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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kina
    0.46
     painfully
    0.44
    herin
    0.44
    angelo
    0.43
    rai
    0.42
    $[
    0.41
    directly
    0.41
    лын
    0.40
     raisin
    0.40
    al
    0.40
    POSITIVE LOGITS
    实习
    0.49
    修复
    0.48
     것을
    0.47
     δημο
    0.45
    utional
    0.44
    堝
    0.44
     중
    0.44
    얽
    0.44
    适合
    0.44
    ător
    0.43
    Act Density 0.003%

    No Known Activations