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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pager
    -0.07
    AGENT
    -0.07
    ulur
    -0.06
     occupation
    -0.06
     其
    -0.06
    xpath
    -0.06
     webView
    -0.06
    mary
    -0.06
    weets
    -0.06
    paypal
    -0.06
    POSITIVE LOGITS
    能
    0.07
     т
    0.06
    >)↵
    0.06
     foc
    0.06
    -msg
    0.06
     withdrawn
    0.06
    according
    0.06
     |
    0.06
    win
    0.06
     Пет
    0.06
    Act Density 0.017%

    No Known Activations