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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ह्या
    0.80
    hanna
    0.79
     plucked
    0.79
    hovah
    0.77
     nenhum
    0.76
     paraphr
    0.76
     vorbere
    0.76
    мни
    0.75
     pebb
    0.75
     zarar
    0.75
    POSITIVE LOGITS
    م
    0.81
    ์
    0.81
    强度
    0.80
    itting
    0.76
    routingHeader
    0.73
     Andi
    0.72
    Consumption
    0.71
     consumption
    0.68
     lét
    0.68
    𝚊
    0.68
    Act Density 0.000%

    No Known Activations