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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     controversies
    0.76
     controversy
    0.71
    閬
    0.71
    ]
    0.69
    –
    0.68
    >)
    0.67
     pathophysiology
    0.66
     विधेयक
    0.66
    );
    0.65
    feasible
    0.65
    POSITIVE LOGITS
    س
    0.86
    ल
    0.82
     Chin
    0.80
     tmux
    0.72
    cou
    0.72
    ي
    0.71
     tüm
    0.71
    ás
    0.68
    ka
    0.68
    ق
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.