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

    Neuronpedia

    INDEX
    Explanations

    Postal Accountability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅದರ
    0.47
     याची
    0.45
    Personensuche
    0.43
     কয়েক
    0.43
    salaryfrom
    0.42
    人心
    0.42
    သ
    0.42
     ايا
    0.42
    ໄຂ
    0.42
    ・・・。
    0.41
    POSITIVE LOGITS
     K
    0.39
     Jedi
    0.38
     rooted
    0.38
     recap
    0.37
     -
    0.37
     met
    0.36
     research
    0.36
    strings
    0.36
     Konink
    0.36
     reasoning
    0.36
    Act Density 0.002%

    No Known Activations