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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    in
    0.48
     shut
    0.46
    </h2>
    0.46
    idikan
    0.44
     p
    0.43
     life
    0.42
     stress
    0.42
     fr
    0.42
     suppressed
    0.42
    s
    0.41
    POSITIVE LOGITS
    ນາ
    0.55
    $-(
    0.53
    ⵃ
    0.52
    તુ
    0.50
    combinations
    0.49
    ન્ડ
    0.49
    ິ
    0.49
    ວຍ
    0.48
    км
    0.48
    ங்க்
    0.48
    Act Density 0.000%

    No Known Activations