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

    Neuronpedia

    INDEX
    Explanations

    plural organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.58
     on
    0.54
     いう
    0.50
     valuable
    0.49
     Já
    0.48
     读取
    0.47
    发
    0.47
     Trường
    0.47
     غير
    0.47
     没有
    0.46
    POSITIVE LOGITS
     corporations
    0.70
     democracies
    0.68
     multinationals
    0.63
     organisations
    0.60
     religions
    0.59
     universities
    0.59
     museums
    0.59
    organizations
    0.59
     nonprofits
    0.57
    0
    0.57
    Act Density 0.500%

    No Known Activations