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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    okovic
    0.92
    osiery
    0.84
    renees
    0.83
     indicato
    0.78
    天气
    0.76
     sním
    0.74
    іб
    0.73
     слегка
    0.73
    偶尔
    0.73
     उक्त
    0.73
    POSITIVE LOGITS
    𝐖
    0.97
     heterogeneous
    0.95
     heterogeneity
    0.88
     amounted
    0.87
    𝐓
    0.86
     restructured
    0.84
    뺏
    0.83
     wid
    0.83
    芰
    0.83
     destruct
    0.82
    Act Density 0.000%

    No Known Activations