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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hubbard
    0.41
    <0x80>
    0.40
     importância
    0.40
     desenvol
    0.40
     опу
    0.39
    urés
    0.39
     नष्ट
    0.38
     proteção
    0.37
     статью
    0.37
    $.}
    0.37
    POSITIVE LOGITS
    י
    0.61
    ה
    0.57
    ז
    0.48
    ייה
    0.47
     regret
    0.46
     decomposes
    0.46
    ט
    0.45
    غ
    0.45
    🥲
    0.45
    ת
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.