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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HAVING
    0.56
     having
    0.54
    having
    0.47
    Having
    0.46
     Having
    0.46
     NOT
    0.45
     ayant
    0.45
    ग्गा
    0.41
     وصف
    0.41
    ,…
    0.39
    POSITIVE LOGITS
     def
    0.37
     মশ
    0.37
     deles
    0.36
    *>(
    0.36
     large
    0.35
     horticultural
    0.35
     modifying
    0.34
    ToWrite
    0.34
     ക
    0.34
    "]]
    0.34
    Act Density 0.004%

    No Known Activations