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

    Neuronpedia

    INDEX
    Explanations

    software libraries and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বলিয়াই
    0.34
    ಾದರೂ
    0.32
     ہاتھ
    0.30
     తెలు
    0.30
    𝗕
    0.29
    ModelGrid
    0.29
    NumberOperation
    0.29
     headway
    0.29
    ഹ്ലാദ
    0.29
    𝘣
    0.29
    POSITIVE LOGITS
    ®
    0.48
    ®,
    0.46
    ®.
    0.42
    或其他
    0.42
    Ⓡ
    0.41
    /
    0.41
    ™
    0.40
    )
    0.38
    .
    0.37
    ,
    0.37
    Act Density 0.331%

    No Known Activations