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

    Neuronpedia

    INDEX
    Explanations

    eyes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLUD
    -0.08
    orge
    -0.07
    SWG
    -0.07
    �
    -0.07
    厳
    -0.06
    _that
    -0.06
     expansion
    -0.06
    -existing
    -0.06
    襄阳
    -0.06
    企图
    -0.06
    POSITIVE LOGITS
    Instruction
    0.09
    近日
    0.08
    rules
    0.07
    抽查
    0.07
     hospitals
    0.07
    扫
    0.07
     proactive
    0.06
    .•
    0.06
    "display
    0.06
    Namespace
    0.06
    Act Density 0.014%

    No Known Activations