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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TOKEN
    -0.07
     casualty
    -0.07
     fitness
    -0.07
     ==========
    -0.07
     Communities
    -0.07
    /env
    -0.07
     encounters
    -0.07
     organizing
    -0.06
    stick
    -0.06
     encounter
    -0.06
    POSITIVE LOGITS
     UIKit
    0.07
    .Xna
    0.06
    operator
    0.06
    volatile
    0.06
    妻
    0.06
     manganese
    0.06
     česk
    0.06
    _CNTL
    0.06
    639
    0.06
     thầu
    0.06
    Act Density 0.285%

    No Known Activations