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

    Neuronpedia

    INDEX
    Explanations

    low, high, if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jerseys
    1.08
     leases
    1.00
     shipments
    0.98
    ementerian
    0.90
     また
    0.88
    unternehmen
    0.87
     savent
    0.87
     这些
    0.87
    存在的
    0.86
    和其他
    0.86
    POSITIVE LOGITS
     (
    0.85
    ,
    0.79
    /
    0.77
     czyli
    0.75
    ;
    0.70
    %,
    0.69
    $,
    0.68
     zalo
    0.67
     Reconstruction
    0.66
    ",
    0.66
    Act Density 0.004%

    No Known Activations