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

    Neuronpedia

    INDEX
    Explanations

    using namespace std

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    2.53
    م
    2.45
     iba
    2.01
    gameObject
    1.99
     ench
    1.98
    ெ
    1.90
    ર
    1.89
     tulaj
    1.87
    াগ
    1.82
     Ammonia
    1.79
    POSITIVE LOGITS
    Согласно
    1.62
    т
    1.58
    した
    1.58
    étera
    1.58
    (;
    1.58
     neige
    1.54
    с
    1.54
    JScripts
    1.53
    ddots
    1.53
    mersible
    1.52
    Act Density 0.030%

    No Known Activations