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

    Neuronpedia

    INDEX
    Explanations

    technical terms and their function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verwend
    0.48
    増加
    0.45
     ከተ
    0.45
     zlat
    0.45
     slik
    0.45
     favorit
    0.44
     sobr
    0.44
     „
    0.44
     人気
    0.44
     वस्त्र
    0.43
    POSITIVE LOGITS
    负责
    0.54
    设计
    0.52
    模块
    0.49
    结构
    0.46
    要做
    0.46
    对
    0.46
    给
    0.46
     firmware
    0.46
     encoding
    0.45
    责任
    0.45
    Act Density 0.007%

    No Known Activations