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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    0.20
    you
    0.19
    but
    0.19
    It
    0.18
     này
    0.17
     It
    0.16
    also
    0.16
    มัน
    0.16
    there
    0.15
     Except
    0.15
    POSITIVE LOGITS
     പുതിയ
    0.16
     establish
    0.16
     onboarding
    0.16
     delineate
    0.15
     പ്രവർത്തന
    0.15
    ⃣
    0.15
     generate
    0.15
     통한
    0.15
     Darstellung
    0.15
     obfusc
    0.15
    Act Density 4.143%

    No Known Activations