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

    Neuronpedia

    INDEX
    Explanations

    Code-related tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	↵↵
    -0.09
    似乎
    -0.07
     sights
    -0.06
     Fifth
    -0.06
     Probably
    -0.06
    :::::
    -0.06
     italian
    -0.06
     통해
    -0.06
    [,
    -0.06
    |↵↵
    -0.06
    POSITIVE LOGITS
     ngx
    0.07
    -controller
    0.07
    .Height
    0.06
    .BLL
    0.06
    锦
    0.06
     eclips
    0.06
    _decision
    0.06
     تبلی
    0.06
    ाइक
    0.06
     BinaryTree
    0.06
    Act Density 0.044%

    No Known Activations