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

    Neuronpedia

    INDEX
    Explanations

    Chris

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ($.
    -0.07
    apan
    -0.07
     turbulent
    -0.06
     },{
    -0.06
     blogging
    -0.06
    _PWR
    -0.06
     Вал
    -0.06
    Expr
    -0.06
    }),
    -0.06
    BrowserRouter
    -0.06
    POSITIVE LOGITS
     redistribute
    0.07
    OfSize
    0.06
     Length
    0.06
     Quotes
    0.06
     उ
    0.06
     іде
    0.06
    ationToken
    0.06
     Mikhail
    0.06
     doğ
    0.06
     Nicola
    0.06
    Act Density 0.022%

    No Known Activations