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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Anyway
    -0.07
     الخام
    -0.07
    הליכי
    -0.07
     günlük
    -0.07
    パ
    -0.07
    extérieur
    -0.06
    独
    -0.06
    _DYNAMIC
    -0.06
    缛
    -0.06
    charger
    -0.06
    POSITIVE LOGITS
    流通
    0.07
    冰淇淋
    0.07
     mitt
    0.07
     shutdown
    0.07
    руж
    0.06
     infected
    0.06
    ulture
    0.06
    _MATCH
    0.06
     cruc
    0.06
     kuruluş
    0.06
    Act Density 0.006%

    No Known Activations