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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     $\
    0.52
     pendant
    0.47
     podr
    0.46
     Lose
    0.46
     Peker
    0.46
     ş
    0.46
    ``
    0.45
    [];
    0.45
     chale
    0.45
     Năm
    0.45
    POSITIVE LOGITS
    neat
    0.50
    Pipeline
    0.49
    kx
    0.49
    y
    0.49
    kong
    0.48
    very
    0.47
    صاف
    0.46
    plc
    0.45
    peak
    0.45
    PLL
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.