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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     تصير
    0.50
     Phang
    0.49
    leftharpoons
    0.49
    o
    0.48
    ר
    0.48
     koska
    0.47
    ượng
    0.47
    ressant
    0.46
    ช่วย
    0.46
     shutterstock
    0.46
    POSITIVE LOGITS
     in
    0.51
     imperatives
    0.50
    မ္
    0.49
    nesses
    0.44
    hips
    0.42
     artisan
    0.42
     aliments
    0.42
     हजार
    0.42
    ،
    0.42
     croissants
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.