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

    Neuronpedia

    INDEX
    Explanations

    solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你在
    0.44
    కరణ
    0.44
    笔记本
    0.41
    IME
    0.41
     nhất
    0.40
     krás
    0.39
    每一
    0.39
     vykon
    0.39
    ITION
    0.37
    ATION
    0.37
    POSITIVE LOGITS
     해결
    0.68
     solution
    0.67
     soluções
    0.65
    解决方案
    0.64
     Lösungen
    0.64
     solutions
    0.63
     Lösung
    0.63
     soluzione
    0.63
     megold
    0.63
     Solution
    0.63
    Act Density 0.146%

    No Known Activations