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

    Neuronpedia

    INDEX
    Explanations

    1990s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regard
    0.75
     sovereignty
    0.70
     lâ
    0.70
     desac
    0.69
     fascin
    0.69
     péri
    0.68
     unbear
    0.67
    ments
    0.66
     \[
    0.66
     sustenance
    0.65
    POSITIVE LOGITS
    9
    0.94
    8
    0.93
    6
    0.85
    5
    0.85
    ης
    0.84
    7
    0.83
    ый
    0.82
     FutureWarning
    0.81
    czyny
    0.81
     kiện
    0.80
    Act Density 0.008%

    No Known Activations