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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    נ
    0.84
    ول
    0.82
    미
    0.82
    ش
    0.79
    श
    0.79
    ח
    0.76
    買
    0.73
    ロ
    0.73
    车
    0.72
    어
    0.71
    POSITIVE LOGITS
    на
    0.95
    hältnisse
    0.84
    аны
    0.83
     Processes
    0.79
    step
    0.77
    stands
    0.74
    ść
    0.74
     ∑
    0.73
     расстоя
    0.73
    processes
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.