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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     whipping
    0.42
    uddho
    0.42
     Marxist
    0.40
     curling
    0.40
    好評
    0.39
    culaire
    0.38
     knives
    0.38
     внимание
    0.37
     radiative
    0.37
    㤈
    0.37
    POSITIVE LOGITS
     mana
    0.45
    ק
    0.45
    소
    0.41
     Spent
    0.40
    OR
    0.40
     مدينة
    0.39
     الس
    0.39
    কো
    0.39
     ق
    0.38
     Revista
    0.38
    Act Density 0.000%

    No Known Activations