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

    Neuronpedia

    INDEX
    Explanations

    do this calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CellValue
    0.40
    ക്കേണ്ട
    0.40
     domicile
    0.39
    BURSE
    0.39
     WD
    0.39
     Ains
    0.39
     worded
    0.38
    的回
    0.38
    beni
    0.38
     ocasion
    0.38
    POSITIVE LOGITS
     plug
    0.46
    plug
    0.46
    Plug
    0.45
     plugged
    0.42
    决策
    0.40
    Visitor
    0.39
    这些
    0.39
    fu
    0.39
     fou
    0.39
     plugs
    0.38
    Act Density 0.000%

    No Known Activations