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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ente
    1.07
    Տ
    1.02
     wid
    0.99
    Stor
    0.98
    exp
    0.97
    ISTA
    0.96
    uma
    0.94
    Poly
    0.93
    BA
    0.93
    K
    0.92
    POSITIVE LOGITS
     फैशन
    1.19
    ьте
    1.19
    ്
    1.13
    !!.
    1.12
     mantan
    1.09
     endeavor
    1.09
    劑
    1.08
    ‪‬
    1.08
     schematically
    1.08
     пул
    1.07
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.