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

    Neuronpedia

    INDEX
    Explanations

    Receipts and expenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Helsinki
    -0.08
    הל
    -0.08
     Toggle
    -0.08
     Swim
    -0.08
     pregnant
    -0.08
     swimmers
    -0.08
     swimming
    -0.07
     Aquarius
    -0.07
     okw
    -0.07
     mellow
    -0.07
    POSITIVE LOGITS
     receipts
    0.09
     receipt
    0.09
     issued
    0.08
    下载
    0.08
    出处
    0.08
    据
    0.08
     thermal
    0.08
    _download
    0.08
     aé
    0.08
    编号
    0.07
    Act Density 0.014%

    No Known Activations