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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    н
    1.52
    ン
    1.48
    ن
    1.38
     principes
    1.21
    ν
    1.14
    <unused2140>
    1.11
    нном
    1.09
     locaux
    1.07
    ст
    1.06
    あまり
    1.00
    POSITIVE LOGITS
     .
    1.29
    .)
    1.20
     )
    1.15
    하다
    1.09
     .)
    1.06
    j
    1.05
    다
    1.05
     ,
    0.98
    는
    0.93
    ation
    0.93
    Act Density 0.000%

    No Known Activations