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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Blooming
    0.66
    bright
    0.64
    ABCD
    0.63
    Bright
    0.62
    amounts
    0.62
    intervals
    0.61
    high
    0.60
    amount
    0.60
    কাশ
    0.60
    ampshire
    0.60
    POSITIVE LOGITS
     👇
    0.76
    👇
    0.63
    ッパー
    0.57
     👉
    0.56
     👋
    0.55
     tanti
    0.54
     sowohl
    0.53
     relacionadas
    0.53
     😊
    0.53
     nuanced
    0.53
    Act Density 0.000%

    No Known Activations