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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     majestic
    0.41
     Denne
    0.41
     rife
    0.41
     Zoe
    0.40
     famously
    0.39
     weekdays
    0.39
     nationwide
    0.39
     ductile
    0.39
     browsing
    0.39
     spectrogram
    0.39
    POSITIVE LOGITS
    ឹម
    0.38
     сразу
    0.38
    ()}
    0.37
    产权
    0.36
    耳机
    0.36
    芾
    0.36
    ષા
    0.36
    //}
    0.35
    壹章
    0.35
    Cache
    0.35
    Act Density 0.000%

    No Known Activations