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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğini
    0.49
    offerta
    0.43
     Archdiocese
    0.43
     wład
    0.43
    出门
    0.43
     Justiça
    0.42
    ifikasi
    0.42
     olması
    0.42
     anuncia
    0.42
    新闻
    0.41
    POSITIVE LOGITS
    [],
    0.37
    ,$$
    0.37
    Xs
    0.36
    ᵢ
    0.36
    $,
    0.36
     algebraically
    0.36
    ldots
    0.34
     등을
    0.34
    (),
    0.33
    (-
    0.33
    Act Density 0.166%

    No Known Activations