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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﻰ
    0.74
    定律
    0.73
     manometer
    0.73
     বসিয়
    0.72
     With
    0.71
     Trên
    0.71
     насы
    0.71
     Alberts
    0.70
    anganese
    0.70
    ೊಂದಿಗೆ
    0.70
    POSITIVE LOGITS
    只不过
    0.69
     haute
    0.66
    لم
    0.66
    ני
    0.65
    نیا
    0.65
    ,
    0.65
     얼마
    0.65
     voic
    0.65
    çando
    0.65
    Existing
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.