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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    name
    1.16
    ps
    1.09
    ment
    1.02
    elif
    0.96
    ק
    0.94
    inizin
    0.87
    ination
    0.85
    ac
    0.85
    tr
    0.84
    ía
    0.83
    POSITIVE LOGITS
    IN
    1.33
    U
    1.20
    THING
    1.20
    N
    1.12
    एस
    1.10
     evam
    1.02
     kanan
    1.02
    }])
    1.01
    RICAL
    1.00
     akhir
    0.97
    Act Density 0.105%

    No Known Activations