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

    Neuronpedia

    INDEX
    Explanations

    Gemma team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有很多
    0.43
     Pltf
    0.40
    िफिकेट
    0.39
    绁
    0.39
     Yamazaki
    0.38
    溂
    0.38
     exaggeration
    0.38
     গ্রস্থ
    0.38
    akkhanam
    0.38
    रेशन
    0.38
    POSITIVE LOGITS
    ，
    0.47
    ،
    0.46
    $,
    0.45
    、
    0.45
     piccoli
    0.38
     quien
    0.38
     commande
    0.38
     in
    0.37
     في
    0.37
    spiele
    0.37
    Act Density 0.068%

    No Known Activations