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

    Neuronpedia

    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turmoil
    -0.06
    تی
    -0.06
     predators
    -0.06
    (Icons
    -0.06
     Care
    -0.06
    (search
    -0.06
     菲律宾
    -0.06
    яч
    -0.06
     televizyon
    -0.06
    ,date
    -0.06
    POSITIVE LOGITS
    선
    0.07
    manual
    0.06
    mn
    0.06
     experimental
    0.06
     sunny
    0.06
    unden
    0.06
    Categories
    0.06
     administer
    0.06
    bands
    0.06
    Tu
    0.06
    Act Density 0.006%

    No Known Activations