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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    0.87
    сным
    0.84
    sama
    0.81
     emocion
    0.81
     Cuomo
    0.80
    classe
    0.80
    Dus
    0.78
    ة
    0.78
    ់
    0.78
    Lit
    0.77
    POSITIVE LOGITS
     remained
    0.78
     midwife
    0.77
     hemisphere
    0.77
     remembered
    0.73
     verifying
    0.73
     refrained
    0.72
     believed
    0.71
     squarely
    0.70
     toothbrush
    0.69
     visualizing
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.