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

    Neuronpedia

    INDEX
    Explanations

    content descriptions and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그걸
    0.70
     eukary
    0.70
    gf
    0.69
     bunu
    0.69
    லோச
    0.68
    一樣
    0.67
    敒
    0.67
     videogame
    0.67
    机器学习
    0.67
    㖑
    0.66
    POSITIVE LOGITS
    これらの
    0.70
     rankings
    0.69
     Series
    0.68
     очеред
    0.68
     कितने
    0.67
    どの
    0.66
    队伍
    0.65
     series
    0.65
    zczeg
    0.65
     самих
    0.65
    Act Density 0.443%

    No Known Activations