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

    Neuronpedia

    INDEX
    Explanations

    model created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పరిశ
    0.40
    FrameworkElement
    0.40
    舉
    0.39
    المل
    0.37
    িত্ত
    0.37
     حرکت
    0.37
    મે
    0.37
    ামের
    0.37
    ாரின்
    0.36
    都不是
    0.36
    POSITIVE LOGITS
    也就是说
    0.45
    这意味着
    0.40
    类似
    0.40
     Cub
    0.39
     Crafted
    0.39
     nghĩa
    0.37
     anlamına
    0.37
     BOP
    0.37
     Package
    0.36
     manufactured
    0.35
    Act Density 0.004%

    No Known Activations