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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Lf
    0.41
    Ꭱ
    0.37
     اللا
    0.36
     notor
    0.36
    Alz
    0.36
    Ethereum
    0.35
     ज्यात
    0.35
    Deborah
    0.35
    irlik
    0.35
     trä
    0.34
    POSITIVE LOGITS
     Host
    0.47
    䒷
    0.46
     communicating
    0.43
    রন
    0.43
    shoot
    0.42
    Host
    0.42
     host
    0.41
     commun
    0.41
     HOST
    0.40
     communication
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.