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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    80
    -0.07
     wash
    -0.07
     married
    -0.07
     imports
    -0.06
    olving
    -0.06
    National
    -0.06
     learned
    -0.06
     Lessons
    -0.06
     kids
    -0.06
     Ann
    -0.06
    POSITIVE LOGITS
     aqu
    0.07
     ков
    0.06
     अपन
    0.06
    /ph
    0.06
    (amount
    0.06
    :::::::
    0.06
    ?>:</
    0.06
     Herr
    0.06
     hypert
    0.06
     swal
    0.06
    Act Density 0.241%

    No Known Activations