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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kinetics
    0.82
    𝑛
    0.78
     누구
    0.75
    inology
    0.74
     worded
    0.72
    इन
    0.72
     Tämä
    0.72
    ১
    0.71
     মহাশ
    0.71
    স
    0.70
    POSITIVE LOGITS
     sare
    0.65
    pares
    0.63
    ıyla
    0.62
    mehr
    0.61
     زیادی
    0.61
    et
    0.60
     хора
    0.59
     $<
    0.59
    ারে
    0.58
    ди
    0.58
    Act Density 0.333%

    No Known Activations