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

    Neuronpedia

    INDEX
    Explanations

    YouTube videos/channels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inactive
    -0.08
    ottage
    -0.08
    Inactive
    -0.07
     identical
    -0.07
     pathway
    -0.07
    account
    -0.07
    inactive
    -0.07
    educt
    -0.07
     Senators
    -0.07
     senators
    -0.07
    POSITIVE LOGITS
     antics
    0.10
     расслед
    0.09
     التحقيق
    0.09
     ocas
    0.09
     goofy
    0.09
     occasional
    0.09
     rant
    0.09
    合集
    0.09
     tackles
    0.08
    企
    0.08
    Act Density 0.045%

    No Known Activations