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

    Neuronpedia

    INDEX
    Explanations

    activism, protests, and dissent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GAAP
    0.77
     Admissions
    0.75
     WebView
    0.73
     Convolution
    0.72
    ="...">
    0.70
     Preview
    0.67
    poruč
    0.67
    加载
    0.67
    Preview
    0.66
    妤
    0.66
    POSITIVE LOGITS
     protests
    3.36
     protest
    3.35
     protesting
    3.02
     protesters
    2.92
     Protest
    2.89
     protestors
    2.83
     protesta
    2.66
     protes
    2.64
     protested
    2.62
     activism
    2.54
    Act Density 0.356%

    No Known Activations