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

    Neuronpedia

    INDEX
    Explanations

    specific items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     penguins
    0.48
    Throw
    0.46
    ్రో
    0.44
    ওয়ার
    0.43
    ႇ
    0.43
    ელი
    0.43
    #!/
    0.42
    jskim
    0.42
     რომელიც
    0.42
    ்டர்
    0.42
    POSITIVE LOGITS
     ஆலோச
    0.41
     homeschool
    0.40
    ká
    0.39
     Advantage
    0.39
    を活用
    0.39
    各種
    0.38
    ამე
    0.38
     Network
    0.37
     wyłącznie
    0.37
    带宽
    0.37
    Act Density 0.002%

    No Known Activations