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

    Neuronpedia

    INDEX
    Explanations

    Line followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aul
    0.39
     APIDC
    0.39
    मस्कार
    0.37
    HasFieldError
    0.36
     pabc
    0.36
    Carolina
    0.36
    Caroline
    0.36
    ងឺ
    0.36
     PAUL
    0.35
    ভিয়েতনাম
    0.35
    POSITIVE LOGITS
     Ku
    0.44
     rib
    0.42
     Rib
    0.40
     ku
    0.37
     Le
    0.37
     Branch
    0.37
     ку
    0.36
     Shir
    0.35
     Smith
    0.35
     college
    0.34
    Act Density 0.015%

    No Known Activations