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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    reiche
    0.86
     활
    0.80
    ektion
    0.80
    pos
    0.77
    izi
    0.77
    p
    0.77
    шил
    0.73
    iet
    0.72
    epoch
    0.72
    ె
    0.72
    POSITIVE LOGITS
     idk
    1.09
     whim
    0.97
    Ἡ
    0.97
    今回の
    0.95
    伨
    0.93
     minivan
    0.93
     HelloWorld
    0.92
     Religious
    0.92
     womb
    0.91
     Literally
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.