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

    Neuronpedia

    INDEX
    Explanations

    more comparative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aa
    1.12
    le
    1.10
    ians
    1.00
    ody
    1.00
    ingly
    1.00
    ১৪
    0.96
    aaaa
    0.94
    \{
    0.93
    movies
    0.92
    MAE
    0.90
    POSITIVE LOGITS
    رخ
    1.05
     того
    1.04
    पणा
    1.02
     numArray
    1.02
    unati
    1.01
    <unused19>
    1.00
    ্স
    1.00
    yawa
    0.98
     aşağıdaki
    0.97
    нам
    0.97
    Act Density 0.151%

    No Known Activations