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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Increases
    0.48
     नये
    0.47
     SoaException
    0.46
    izz
    0.46
     diminishes
    0.46
     образу
    0.45
     cầu
    0.45
    ened
    0.45
     اسے
    0.45
    ilient
    0.45
    POSITIVE LOGITS
    ك
    0.59
    к
    0.55
    क
    0.54
    Как
    0.52
    Ми
    0.52
    世
    0.52
    世界
    0.51
    สวัสดี
    0.51
    如
    0.50
    Hallo
    0.50
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.