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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ্ড
    1.80
    meria
    1.77
    éfonos
    1.77
    ARAJYA
    1.75
    ментів
    1.72
    mería
    1.71
    naments
    1.71
    culas
    1.70
    मिथ
    1.70
    undant
    1.67
    POSITIVE LOGITS
    1.42
     trip
    1.41
     Head
    1.38
    с
    1.34
     bat
    1.30
     de
    1.28
     decade
    1.26
     rec
    1.24
     shift
    1.24
     na
    1.23
    Act Density 0.002%

    No Known Activations