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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wach
    0.78
    ție
    0.74
    こと
    0.73
     konk
    0.73
    ัญญา
    0.72
     dems
    0.71
    ات
    0.70
     bzw
    0.69
    `
    0.69
     vergleich
    0.69
    POSITIVE LOGITS
     malah
    0.78
    痳
    0.75
     misguided
    0.74
    订
    0.74
     indors
    0.73
    сыз
    0.72
     oiled
    0.71
     saudara
    0.71
     मक
    0.70
    推动
    0.69
    Act Density 0.001%

    No Known Activations