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

    Neuronpedia

    INDEX
    Explanations

    past anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vaccine
    -0.08
    OrElse
    -0.07
    =new
    -0.07
     doors
    -0.07
    ाहरण
    -0.06
    oves
    -0.06
    CRM
    -0.06
    ubbles
    -0.06
    .getParameter
    -0.06
    -content
    -0.06
    POSITIVE LOGITS
     Status
    0.06
    หย
    0.06
    UNC
    0.06
     ilan
    0.06
    mus
    0.06
     Traff
    0.06
     Typography
    0.06
     flavored
    0.05
     onay
    0.05
     příprav
    0.05
    Act Density 0.059%

    No Known Activations