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

    Neuronpedia

    INDEX
    Explanations

    High Definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semplici
    0.42
    语
    0.38
    ˆ‚
    0.38
     entrop
    0.37
    对象
    0.37
    emaker
    0.36
    ی
    0.36
     articol
    0.36
     propria
    0.35
    آ
    0.35
    POSITIVE LOGITS
     High
    0.58
     HD
    0.55
    High
    0.54
     Высо
    0.54
    HD
    0.49
     high
    0.49
    高
    0.47
    高清
    0.46
     عالية
    0.45
    high
    0.45
    Act Density 0.007%

    No Known Activations