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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    array
    -0.06
    ThreadPool
    -0.06
     aroused
    -0.06
    .Topic
    -0.06
    olini
    -0.06
    🧿
    -0.06
    -connect
    -0.06
    .UserInfo
    -0.06
    YPE
    -0.06
     armed
    -0.06
    POSITIVE LOGITS
    elah
    0.08
    廉价
    0.07
    ',[
    0.07
    推广应用
    0.07
     Mim
    0.07
    	swap
    0.07
     classics
    0.07
     lightweight
    0.07
    เกม
    0.07
    <tr
    0.07
    Act Density 0.024%

    No Known Activations