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

    Neuronpedia

    INDEX
    Explanations

    garbage collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    来的
    -0.07
    oauth
    -0.07
    .frequency
    -0.07
     Iss
    -0.07
    _vals
    -0.06
    相关部门
    -0.06
    溫
    -0.06
    accel
    -0.06
    thead
    -0.06
    빛
    -0.06
    POSITIVE LOGITS
    (slice
    0.08
     DriverManager
    0.07
    殖
    0.07
     gardening
    0.07
     Rodrig
    0.07
     хотя
    0.07
    欺
    0.07
     connector
    0.07
    架子
    0.07
     parsley
    0.07
    Act Density 0.016%

    No Known Activations