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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ный
    0.92
    sproz
    0.88
    នេះ
    0.88
    skraft
    0.88
     às
    0.87
    های
    0.84
    sprogram
    0.84
     coisas
    0.82
    durch
    0.82
     PDEs
    0.81
    POSITIVE LOGITS
    де
    0.66
    نس
    0.66
    雳
    0.65
    かったです
    0.62
    if
    0.62
    نز
    0.61
    皆さん
    0.61
    プル
    0.60
    ung
    0.60
     droite
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.