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

    Neuronpedia

    INDEX
    Explanations

    Making claims or arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stupid
    -0.09
     stupidity
    -0.08
     cruelty
    -0.08
     :)↵↵
    -0.08
     lud
    -0.08
    োদ
    -0.08
     ridiculous
    -0.08
    เรีย
    -0.08
    ительность
    -0.07
    ুলি
    -0.07
    POSITIVE LOGITS
     previstos
    0.09
    Projected
    0.07
     ERP
    0.07
     MRI
    0.07
     शादी
    0.07
     Sharma
    0.07
     previstas
    0.07
     திரும
    0.07
     größten
    0.07
     Wagner
    0.07
    Act Density 0.022%

    No Known Activations