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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ;
    0.75
    ).
    0.69
    {
    0.61
    و
    0.60
    {})
    0.58
    ).}
    0.57
    ని
    0.57
    <0x80>
    0.56
    1
    0.56
    ),
    0.55
    POSITIVE LOGITS
    -
    0.84
    л
    0.72
    ל
    0.66
    н
    0.61
    ת
    0.60
    もの
    0.57
    け
    0.57
    店の
    0.55
    町の
    0.55
    ी
    0.54
    Act Density 0.000%

    No Known Activations