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

    Neuronpedia

    INDEX
    Explanations

    list item separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogenannten
    0.42
    {}".
    0.42
     {}'.
    0.41
    രുദ്ധ
    0.41
     {}".
    0.41
    {}'.
    0.39
     latter
    0.37
    ણને
    0.36
    <unused4>
    0.35
    abilirsiniz
    0.35
    POSITIVE LOGITS
    、
    1.60
    ,
    1.23
    ،
    1.20
    ၊
    1.13
     、
    1.13
    ፣
    1.11
    -,
    1.07
     ,
    1.05
    ，
    1.01
    ﹑
    0.97
    Act Density 0.713%

    No Known Activations