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

    Neuronpedia

    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sprite
    -0.08
    Hall
    -0.08
    Connector
    -0.07
    大约
    -0.07
    	description
    -0.07
    副秘书长
    -0.07
    (Code
    -0.06
     Band
    -0.06
    enaire
    -0.06
    　
    -0.06
    POSITIVE LOGITS
    的根本
    0.08
    骊
    0.07
     �
    0.07
    (is
    0.07
     intuition
    0.07
    ふ
    0.07
     ${({
    0.06
    Things
    0.06
    ,cp
    0.06
     contrario
    0.06
    Act Density 0.313%

    No Known Activations