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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     aplatis
    0.78
    '
    0.71
     plots
    0.70
    icides
    0.69
     pellets
    0.67
     trim
    0.66
     officials
    0.65
    ствия
    0.65
     pies
    0.65
    inology
    0.65
    POSITIVE LOGITS
    وت
    0.89
    𝗘
    0.86
    ल्लिंग
    0.85
    śnie
    0.83
     concetto
    0.82
    concepto
    0.78
    ﺎ
    0.77
    igenschaft
    0.76
    𝗜
    0.76
    𝗚
    0.76
    Act Density 0.467%

    No Known Activations