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

    Neuronpedia

    INDEX
    Explanations

    social organizations and jurisdictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.70
    會
    0.58
     at
    0.56
     to
    0.51
    on
    0.50
    of
    0.49
    能
    0.48
     an
    0.46
    b
    0.46
     is
    0.45
    POSITIVE LOGITS
    -
    0.71
    ли
    0.54
     theatres
    0.48
     orchestras
    0.48
     parishes
    0.47
     mosques
    0.47
    ,
    0.47
    )
    0.47
     entreprises
    0.46
     piatta
    0.46
    Act Density 0.339%

    No Known Activations