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

    Neuronpedia

    INDEX
    Explanations

    user agents, detection, SGD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    컫
    0.49
     Device
    0.49
     espécie
    0.48
     eszk
    0.45
     PANEL
    0.45
     loài
    0.44
     zařízení
    0.44
     设备
    0.43
     Voy
    0.43
     ê
    0.43
    POSITIVE LOGITS
    জগ
    0.54
    ج
    0.53
     nonchal
    0.46
     كن
    0.45
    正则表达式
    0.42
    瀆
    0.42
    Μ
    0.42
     terse
    0.42
    _.
    0.42
    你
    0.42
    Act Density 0.005%

    No Known Activations