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

    Neuronpedia

    INDEX
    Explanations

    Python code explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chongqing
    0.40
     उतार
    0.40
     గారి
    0.40
     Regis
    0.39
     Samurai
    0.39
     Kiwi
    0.39
     पर्
    0.37
     Howard
    0.37
     Hun
    0.37
     Ephesus
    0.37
    POSITIVE LOGITS
     चलेगा
    0.38
    ＊
    0.37
    Kob
    0.36
    үкт
    0.36
     女性
    0.35
    0.35
    ᐛ
    0.35
     evas
    0.34
    kuk
    0.34
     *);
    0.34
    Act Density 0.006%

    No Known Activations