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

    Neuronpedia

    INDEX
    Explanations

    mountain names, weather, peaks, range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ता
    1.37
    들이
    1.30
    ،
    1.23
    का
    1.20
     време
    1.18
    ၷ
    1.17
     activos
    1.16
    𝔹
    1.15
     крупных
    1.13
     पदाधिकारियों
    1.12
    POSITIVE LOGITS
    r
    2.02
    .
    1.74
    n
    1.68
    a
    1.66
    -
    1.52
    ing
    1.51
    t
    1.37
    ه
    1.35
    an
    1.30
     was
    1.30
    Act Density 0.006%

    No Known Activations