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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    м
    1.08
    je
    1.04
    ك
    1.04
    em
    0.97
    et
    0.96
    я
    0.95
    ic
    0.94
    u
    0.94
    ى
    0.93
     الخ
    0.89
    POSITIVE LOGITS
    ecção
    1.46
    coconut
    1.32
    readonly
    1.29
    Appuntamento
    1.29
    또한
    1.29
     adott
    1.29
     sakit
    1.26
     lepton
    1.26
     besteht
    1.25
    Beware
    1.25
    Act Density 0.000%

    No Known Activations