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

    Neuronpedia

    INDEX
    Explanations

    scripting and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     norms
    0.46
    工作
    0.40
    冠
    0.39
     climático
    0.39
     watert
    0.38
     tienden
    0.38
     iodide
    0.37
    T
    0.37
    ロット
    0.37
    人文
    0.37
    POSITIVE LOGITS
    แหน่ง
    0.50
    㞖
    0.48
     می‌دهد
    0.48
     확인
    0.47
     Poppy
    0.46
     війни
    0.46
     \}
    0.45
     Fallen
    0.45
     Embro
    0.45
     û
    0.45
    Act Density 0.008%

    No Known Activations