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

    Neuronpedia

    INDEX
    Explanations

    furnished

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.13
     on
    0.93
    ف
    0.89
    t
    0.87
     。
    0.78
     i
    0.77
    c
    0.76
    d
    0.72
    _
    0.71
    de
    0.71
    POSITIVE LOGITS
     furnish
    1.06
     furnishings
    1.05
    し
    1.02
     FURN
    1.02
    ζ
    1.00
     muebles
    0.95
    ления
    0.91
    ח
    0.91
    τα
    0.91
    padă
    0.90
    Act Density 0.003%

    No Known Activations