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
    (out
    -0.07
     Bronze
    -0.07
    。，
    -0.07
    �
    -0.07
     coup
    -0.06
     чист
    -0.06
    (cls
    -0.06
    cool
    -0.06
     dismay
    -0.06
    AREN
    -0.06
    POSITIVE LOGITS
    UITableView
    0.07
    назнач
    0.06
     Liberties
    0.06
     newX
    0.06
     ConcurrentHashMap
    0.06
    .mob
    0.06
     Cheers
    0.06
    Monkey
    0.06
    vx
    0.06
    .ver
    0.06
    Act Density 0.041%

    No Known Activations