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

    Neuronpedia

    INDEX
    Explanations

    URLs and web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moitié
    0.39
    ften
    0.37
     sadistic
    0.37
     sinned
    0.35
     símbolo
    0.35
     chacune
    0.34
     chacun
    0.33
     haught
    0.33
     exasper
    0.33
     grotesque
    0.33
    POSITIVE LOGITS
     কিভাবে
    0.35
    旗下
    0.34
    软件
    0.34
    智能
    0.34
    音频
    0.33
    ология
    0.33
    Algorithm
    0.32
    查询
    0.32
    Audio
    0.31
    ＆
    0.31
    Act Density 0.155%

    No Known Activations