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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    S
    0.48
    L
    0.46
    O
    0.46
     locomotor
    0.45
    E
    0.44
    G
    0.43
    り
    0.43
    P
    0.41
    F
    0.40
     retir
    0.39
    POSITIVE LOGITS
     კონ
    0.50
    උ
    0.49
     순간
    0.49
     ਅਤੇ
    0.48
     आणि
    0.46
     осозна
    0.46
     imprend
    0.46
     berlangsung
    0.46
     ജൂ
    0.46
    looked
    0.45
    Act Density 0.003%

    No Known Activations