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

    Neuronpedia

    INDEX
    Explanations

    ideologies and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    付き
    0.79
     ダ
    0.79
    𝙞
    0.77
     ഓ
    0.77
     하기
    0.76
    𝙥
    0.76
    ๐
    0.76
    ے
    0.75
     ਨਾਲ
    0.75
     бі
    0.74
    POSITIVE LOGITS
    ли
    1.19
    ismarck
    0.91
     suffix
    0.91
    geschichte
    0.89
    ศาสตร์
    0.89
     tapestry
    0.87
    лизм
    0.87
    araoh
    0.85
     axiom
    0.84
     clique
    0.83
    Act Density 0.778%

    No Known Activations