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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wody
    0.84
    च
    0.82
    čen
    0.79
    과는
    0.74
    ן
    0.74
    क्
    0.73
    埛
    0.71
    ਾਂ
    0.69
    称
    0.69
    嶅
    0.69
    POSITIVE LOGITS
     Vortex
    0.73
     Discussion
    0.73
     deshalb
    0.71
     били
    0.71
     графика
    0.71
     Entscheidung
    0.69
     публі
    0.69
    arela
    0.68
    autant
    0.68
     treffen
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.