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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     potest
    0.52
    。
    0.49
     direta
    0.47
    妧
    0.47
     gahet
    0.47
     erop
    0.47
     obstáculos
    0.47
    ([\
    0.46
     riesgo
    0.45
    ையா
    0.45
    POSITIVE LOGITS
    ടൊപ്പം
    0.45
    Salv
    0.44
    Square
    0.44
     정사각형
    0.43
     특징
    0.43
    travel
    0.42
    Cl
    0.41
     Travel
    0.41
    Lamb
    0.41
    ۰
    0.41
    Act Density 0.001%

    No Known Activations