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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sixty
    0.89
     ৬০
    0.69
    世
    0.69
    ６
    0.68
    ılmış
    0.66
     liked
    0.66
    acion
    0.65
    ارف
    0.65
    有
    0.65
     thirty
    0.65
    POSITIVE LOGITS
    BasePath
    0.72
     vests
    0.71
     Bromley
    0.68
    Rhe
    0.67
    ക്കൊ
    0.67
     periodically
    0.66
     vest
    0.65
    ✰
    0.64
     चाल
    0.64
    quickly
    0.63
    Act Density 0.000%

    No Known Activations