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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     врач
    0.75
    ZR
    0.71
    hafte
    0.70
     dokter
    0.68
     Search
    0.68
     stimmen
    0.68
    TING
    0.67
     St
    0.66
     Encounter
    0.66
    dz
    0.66
    POSITIVE LOGITS
    的情况下
    0.90
    кої
    0.86
    에
    0.85
    的情況
    0.82
    ان
    0.79
    𝚘
    0.76
     ஆனால்
    0.75
    Neurons
    0.75
    ське
    0.75
    та
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.