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

    Neuronpedia

    INDEX
    Explanations

    authentication routes or tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чные
    0.43
     चाचा
    0.43
     знако
    0.41
     wetting
    0.40
     القسمه
    0.40
    usions
    0.39
    ুব্ধ
    0.38
     undermined
    0.38
     suceder
    0.38
    fice
    0.38
    POSITIVE LOGITS
    Crown
    0.45
     tragedia
    0.40
    HAR
    0.38
    Desktop
    0.38
    ISA
    0.37
    ༸
    0.37
     Crown
    0.37
    굿
    0.37
     …..
    0.36
    ลง
    0.36
    Act Density 0.000%

    No Known Activations