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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    工具
    -0.07
     Caps
    -0.07
     анти
    -0.07
    Any
    -0.07
     By
    -0.06
    ことが
    -0.06
     screenings
    -0.06
     dine
    -0.06
     bm
    -0.06
     checkboxes
    -0.06
    POSITIVE LOGITS
     writers
    0.06
    .PrintWriter
    0.06
    deque
    0.06
    ual
    0.06
    учас
    0.06
    ัญ
    0.06
    leen
    0.06
    (Customer
    0.06
    izzer
    0.06
     ал
    0.06
    Act Density 0.011%

    No Known Activations