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

    Neuronpedia

    INDEX
    Explanations

    notebooks and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powertrain
    0.46
     achieving
    0.45
     APIs
    0.45
     modulation
    0.44
     agrarian
    0.44
     providing
    0.42
     causing
    0.42
     antim
    0.41
     payloads
    0.41
     geopol
    0.40
    POSITIVE LOGITS
    笔记本
    0.82
     notepad
    0.76
     notebook
    0.73
     नोटबुक
    0.73
     бума
    0.68
     Notebook
    0.68
    笔记
    0.67
    notepad
    0.67
     लिखना
    0.65
     노트
    0.65
    Act Density 0.100%

    No Known Activations