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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ال
    1.16
     cleaned
    1.11
     NSObject
    1.11
    री
    1.09
    ट
    1.04
    rove
    1.02
     effected
    1.00
     Σε
    0.98
    ర
    0.98
    ந்த
    0.98
    POSITIVE LOGITS
     Když
    1.00
    Barrier
    1.00
     mesmos
    0.99
    ABLE
    0.99
     неравен
    0.93
     semblable
    0.92
     защото
    0.90
    ablen
    0.88
     אם
    0.88
    zyb
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.