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

    Neuronpedia

    INDEX
    Explanations

    list initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نہایت
    0.42
    Eggs
    0.40
    nahm
    0.39
    ষি
    0.39
    ":"",
    0.39
    铑
    0.38
     strtok
    0.38
    〃
    0.38
    rylic
    0.38
    ="";
    0.38
    POSITIVE LOGITS
     ['
    1.70
     [
    1.63
     ["
    1.57
    =[
    1.43
    =['
    1.41
    =["
    1.38
    ['
    1.38
     [-
    1.32
    ["
    1.31
    ([
    1.29
    Act Density 0.069%

    No Known Activations