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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ευ
    0.42
     संज्ञा
    0.41
     stationary
    0.41
     يعني
    0.40
     ईमान
    0.40
    xlabel
    0.40
     Ejército
    0.39
     sanctuary
    0.39
    <unused28>
    0.39
     toxicity
    0.39
    POSITIVE LOGITS
    Dev
    0.45
    Transl
    0.40
    Deep
    0.40
    Dig
    0.39
    Tert
    0.39
    Plain
    0.39
    Mac
    0.39
    Live
    0.38
    Locked
    0.38
    Kal
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.