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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    RE
    0.55
    IN
    0.54
    Optimization
    0.53
    UR
    0.49
    扎
    0.47
    Quadr
    0.46
    MOR
    0.45
    <sup>
    0.44
    矛盾
    0.44
    Reserved
    0.44
    POSITIVE LOGITS
    ală
    0.50
    ंसिल
    0.50
     nahi
    0.47
    စျေး
    0.47
     gauging
    0.46
    льну
    0.46
    лизи
    0.45
     pasting
    0.44
    andte
    0.44
     satış
    0.43
    Act Density 0.001%

    No Known Activations