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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parcel
    -0.07
     ειδ
    -0.06
    todos
    -0.06
     Advisors
    -0.06
    pper
    -0.06
     soy
    -0.06
    bak
    -0.06
    .CR
    -0.06
    779
    -0.06
     mater
    -0.06
    POSITIVE LOGITS
     installing
    0.06
     форми
    0.06
     assms
    0.06
    .Page
    0.06
     ledna
    0.06
    ikipedia
    0.06
     robbed
    0.06
    reland
    0.06
    ，但
    0.06
    /Create
    0.06
    Act Density 0.081%

    No Known Activations