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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    et
    2.91
    ن
    2.28
    nen
    2.00
    স
    1.91
    de
    1.89
    ल्फ
    1.80
    jenigen
    1.73
    nel
    1.72
    u
    1.71
    犍
    1.70
    POSITIVE LOGITS
    ⬝
    1.99
    েদ
    1.97
     momenta
    1.96
     glycoprotein
    1.91
     cmap
    1.87
     kwargs
    1.86
    CMAKE
    1.85
    Então
    1.84
     momentum
    1.83
     bearish
    1.82
    Act Density 0.001%

    No Known Activations