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

    Neuronpedia

    INDEX
    Explanations

    not constitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Complaint
    0.80
     astrophysical
    0.79
     Complaint
    0.74
     Xác
    0.73
    эро
    0.73
     complaint
    0.73
     ಉತ್ಪನ್ನ
    0.72
     abogados
    0.71
     固定
    0.70
     usare
    0.70
    POSITIVE LOGITS
    intended
    0.83
     কোনও
    0.74
    Decision
    0.73
     intended
    0.72
    upply
    0.72
    Linq
    0.71
    rams
    0.70
    considered
    0.70
    ต่อ
    0.69
    lös
    0.68
    Act Density 0.002%

    No Known Activations