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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wattage
    0.82
     dizzy
    0.81
    ্বরূপ
    0.76
     antire
    0.71
    費
    0.71
     circumfer
    0.70
    титься
    0.70
    共和
    0.70
    チック
    0.70
     bookcases
    0.70
    POSITIVE LOGITS
    che
    0.93
    ים
    0.92
    L
    0.90
     テ
    0.86
    K
    0.85
    h
    0.84
    T
    0.83
    タ
    0.83
     מ
    0.80
    F
    0.80
    Act Density 0.001%

    No Known Activations