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

    Neuronpedia

    INDEX
    Explanations

    official health resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     urgency
    0.67
    意思
    0.66
    繕
    0.65
     hostility
    0.64
    indicators
    0.64
    цима
    0.64
     cường
    0.62
     indicators
    0.62
    lemen
    0.60
     boldness
    0.60
    POSITIVE LOGITS
     Dever
    0.83
    Gov
    0.80
    IBRARY
    0.79
    gov
    0.77
    弈
    0.73
    াবির
    0.73
     পানির
    0.72
     Govern
    0.72
    グッズ
    0.72
     Gavin
    0.72
    Act Density 0.022%

    No Known Activations