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

    Neuronpedia

    INDEX
    Explanations

    seriously sorry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kerak
    0.41
    0.38
    ვა
    0.37
     Spade
    0.36
     Kru
    0.35
    йович
    0.35
     chances
    0.35
    Rum
    0.34
    gren
    0.34
    ycji
    0.34
    POSITIVE LOGITS
     asterisk
    0.44
     flowchart
    0.40
    ^*_{
    0.38
    星
    0.38
     星
    0.37
     contiguous
    0.37
     ব্যাকটেরিয়া
    0.37
    निम
    0.37
     asteroid
    0.36
     quartile
    0.36
    Act Density 0.005%

    No Known Activations