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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ang
    0.51
     valuable
    0.49
    the
    0.48
    ancies
    0.44
    ವುದ
    0.44
     V
    0.42
     queen
    0.42
    smarty
    0.42
     the
    0.41
    ônio
    0.41
    POSITIVE LOGITS
     бетон
    0.53
     setengah
    0.51
     effekt
    0.49
    प्रिंट
    0.49
    𝟮
    0.47
    OUT
    0.46
     ana
    0.46
    ร้อน
    0.46
     Vorteile
    0.45
     επιχει
    0.45
    Act Density 0.003%

    No Known Activations