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

    Neuronpedia

    INDEX
    Explanations

    stating who one is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     footh
    0.42
     has
    0.42
     CG
    0.41
    Mer
    0.41
     thigh
    0.41
     Mer
    0.40
    我が
    0.40
     Timeout
    0.38
     svůj
    0.38
     Laird
    0.38
    POSITIVE LOGITS
    交给
    0.43
    いです
    0.42
    是由
    0.41
     بوده
    0.41
    이고
    0.40
    ovatel
    0.40
     manuss
    0.40
     kidding
    0.38
     ہے
    0.38
     आहेत
    0.38
    Act Density 0.005%

    No Known Activations