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

    Neuronpedia

    INDEX
    Explanations

    DataFrame column names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Les
    0.43
     Render
    0.42
    Brun
    0.42
     Pastel
    0.40
    看到
    0.40
    Natal
    0.39
    Les
    0.38
    Red
    0.38
    ブラシ
    0.37
     las
    0.37
    POSITIVE LOGITS
    tcpHeader
    0.43
    名稱
    0.42
    ارد
    0.39
    cbind
    0.39
     اسمه
    0.39
    teman
    0.38
     names
    0.38
     namn
    0.38
    軧
    0.38
    inado
    0.38
    Act Density 0.073%

    No Known Activations