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

    Neuronpedia

    INDEX
    Explanations

    corporation and corporate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neben
    0.40
     Предпо
    0.40
    功率
    0.39
    기로
    0.38
     supp
    0.38
    力を
    0.38
    ardia
    0.37
    товые
    0.37
    גע
    0.36
     Полу
    0.36
    POSITIVE LOGITS
    por
    0.68
    Por
    0.59
     corporation
    0.58
     corporations
    0.58
     por
    0.57
     корпора
    0.55
    oreal
    0.52
     corpor
    0.52
    corpor
    0.51
     Por
    0.51
    Act Density 0.010%

    No Known Activations