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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cumhuriyet
    -0.06
     countertops
    -0.06
    constraint
    -0.06
     multitude
    -0.06
    kap
    -0.06
    etermine
    -0.06
    uration
    -0.06
    .evaluate
    -0.06
     Nich
    -0.06
    (names
    -0.06
    POSITIVE LOGITS
    λή
    0.07
     vastly
    0.07
    बर
    0.06
    ipse
    0.06
    ştir
    0.06
     Atlanta
    0.06
     announce
    0.06
    imentos
    0.06
     Departments
    0.06
     아이디
    0.06
    Act Density 0.034%

    No Known Activations