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

    Neuronpedia

    INDEX
    Explanations

    _padding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .s
    -0.06
    apper
    -0.06
    很
    -0.06
     Tet
    -0.06
    iệ
    -0.06
    ¼
    -0.06
    (()
    -0.06
    Psi
    -0.06
    .strict
    -0.06
    Compact
    -0.06
    POSITIVE LOGITS
    guard
    0.07
    (Application
    0.07
     CELL
    0.07
    통신
    0.06
    -guard
    0.06
     нового
    0.06
    决定
    0.06
     модели
    0.06
    .reducer
    0.06
     استاد
    0.06
    Act Density 0.090%

    No Known Activations