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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleansing
    -0.07
     electrode
    -0.07
    Fetch
    -0.07
    一键
    -0.07
    FullScreen
    -0.07
    应急管理
    -0.07
    马来
    -0.07
    饲养
    -0.07
    最强
    -0.06
    扇
    -0.06
    POSITIVE LOGITS
     uttered
    0.07
    �
    0.07
     adequately
    0.07
    orias
    0.07
     оп
    0.07
     comprom
    0.06
     nog
    0.06
    �
    0.06
    闺
    0.06
    �
    0.06
    Act Density 0.010%

    No Known Activations