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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    er
    0.54
    د
    0.46
    у
    0.45
    ه
    0.45
     tornando
    0.45
    ر
    0.44
    aue
    0.44
    ровании
    0.43
     تعدى
    0.43
    ikker
    0.41
    POSITIVE LOGITS
    ปี
    0.49
     talisman
    0.49
     yearbook
    0.45
    repet
    0.44
     अंका
    0.44
    ִ
    0.44
    STEAM
    0.44
     機
    0.43
    ̕
    0.43
    resist
    0.43
    Act Density 0.003%

    No Known Activations