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

    Neuronpedia

    INDEX
    Explanations

    moral distress or recreational shooting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عملکرد
    0.40
    価格
    0.39
     honors
    0.38
    Operations
    0.38
    Declared
    0.38
    Пи
    0.37
    性能
    0.36
    靈
    0.36
    setNome
    0.36
     талант
    0.35
    POSITIVE LOGITS
    aviti
    0.39
    incing
    0.39
    cyan
    0.39
    adonis
    0.38
    hões
    0.38
    CONS
    0.38
     Radar
    0.37
     दिलाया
    0.37
    ළ
    0.37
    បង្ហ
    0.37
    Act Density 0.000%

    No Known Activations