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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ط
    0.72
    ແລະ
    0.63
    را
    0.60
    ৭
    0.55
    ăți
    0.54
    ắc
    0.52
    文件中
    0.52
    }\
    0.52
     गर्ल
    0.51
     прошлом
    0.50
    POSITIVE LOGITS
     dotyczą
    0.53
     wody
    0.53
    CUR
    0.50
     संख्याओं
    0.49
     поводу
    0.49
    WHITE
    0.49
     щодо
    0.48
    MIC
    0.48
    SK
    0.48
     mattered
    0.48
    Act Density 0.036%

    No Known Activations