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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unifu
    -0.07
     Modules
    -0.07
     ```
    -0.07
    ONS
    -0.06
     headers
    -0.06
    	all
    -0.06
    ReturnValue
    -0.06
     程
    -0.06
    аду
    -0.06
     通
    -0.06
    POSITIVE LOGITS
     бла
    0.07
     entra
    0.07
     Üst
    0.06
     TBranch
    0.06
    /Desktop
    0.06
     행복
    0.06
     داخل
    0.06
     Augusta
    0.06
     фин
    0.06
     Σεπ
    0.06
    Act Density 0.186%

    No Known Activations