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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nicht
    0.89
     However
    0.79
    ají
    0.79
     பல்வேறு
    0.76
     しかし
    0.76
    azioni
    0.75
    uldu
    0.74
    此外
    0.73
     diverses
    0.71
     Employees
    0.71
    POSITIVE LOGITS
     saturated
    0.83
    ʬ
    0.79
    ко
    0.75
    ק
    0.75
     здрав
    0.74
    ௦
    0.74
    ﻙ
    0.74
     Lyle
    0.73
     tanh
    0.73
    ཌ
    0.73
    Act Density 0.000%

    No Known Activations