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

    Neuronpedia

    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    即时
    -0.07
    .Tree
    -0.07
     NSLog
    -0.07
     treated
    -0.07
     fitted
    -0.07
    交友
    -0.06
     dragging
    -0.06
     hoc
    -0.06
     tous
    -0.06
    Manager
    -0.06
    POSITIVE LOGITS
    guard
    0.08
    本事
    0.07
    _eff
    0.07
     Barrel
    0.07
    .energy
    0.07
    .clients
    0.06
    触れ
    0.06
    ⟱
    0.06
    药
    0.06
    .btnExit
    0.06
    Act Density 0.033%

    No Known Activations