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

    Neuronpedia

    INDEX
    Explanations

    area chart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clots
    0.53
     obej
    0.46
     Chronic
    0.45
     hottest
    0.44
    cute
    0.44
     CAUSED
    0.43
    ގ
    0.43
     เล
    0.41
     parte
    0.41
    ciones
    0.41
    POSITIVE LOGITS
    Version
    0.51
    2
    0.49
    Area
    0.48
    Bert
    0.46
    面积
    0.45
    面積
    0.43
     Hamming
    0.43
     পক্ষে
    0.43
     Bert
    0.42
     एरिया
    0.42
    Act Density 0.005%

    No Known Activations