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

    Neuronpedia

    INDEX
    Explanations

    sales and financial outlooks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ติ
    -0.76
    Lø
    -0.76
     rápida
    -0.76
     prized
    -0.73
    stunde
    -0.73
    唐揚げ
    -0.70
    quierda
    -0.69
    (__
    -0.69
     treasured
    -0.69
     泰
    -0.68
    POSITIVE LOGITS
     like
    1.10
     Comparable
    1.05
     sales
    0.96
     comparable
    0.94
     comparator
    0.91
     compara
    0.90
    comparable
    0.88
     comps
    0.87
     COMPAR
    0.85
    Daf
    0.82
    Act Density 0.015%

    No Known Activations