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

    Neuronpedia

    INDEX
    Explanations

    traceback file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بیاکت
    0.39
    ：%
    0.39
    ამე
    0.39
    渔
    0.36
    thisobject
    0.35
    DeathRecord
    0.35
    gmzy
    0.35
    ার্ভ
    0.34
     závod
    0.34
    法定
    0.34
    POSITIVE LOGITS
     mathsize
    0.48
     mathcolor
    0.47
     mathvariant
    0.40
     দিল্লির
    0.35
     class
    0.34
    > </
    0.33
    ơ
    0.33
     phản
    0.33
    Em
    0.33
    "></
    0.32
    Act Density 0.000%

    No Known Activations