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

    Neuronpedia

    INDEX
    Explanations

    companies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    床
    -0.08
     Geli
    -0.07
    溫
    -0.07
    ())
↵
    -0.07
    �
    -0.07
     currency
    -0.07
    个人信息
    -0.07
    手游
    -0.07
    ments
    -0.07
     Math
    -0.07
    POSITIVE LOGITS
    .freeze
    0.08
    ORIGINAL
    0.07
    安娜
    0.07
    ographers
    0.07
    clarations
    0.07
     intim
    0.07
     astonishing
    0.07
    	dfs
    0.07
    threshold
    0.07
    Forbidden
    0.07
    Act Density 0.046%

    No Known Activations