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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ade
    -0.07
    ITIVE
    -0.07
    kode
    -0.07
     contrasting
    -0.06
     leaned
    -0.06
    stad
    -0.06
    faker
    -0.06
    *:
    -0.06
     FETCH
    -0.06
     Joyce
    -0.06
    POSITIVE LOGITS
    \uD
    0.07
    yš
    0.06
    .Vert
    0.06
    [:-
    0.06
     интерес
    0.06
     McDonald
    0.06
    salary
    0.06
     IDR
    0.06
    mm
    0.06
     TempData
    0.06
    Act Density 0.042%

    No Known Activations