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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .STATE
    -0.07
     उम
    -0.07
     ix
    -0.06
    ↵↵↵↵↵↵↵
    -0.06
    webElementProperties
    -0.06
     ye
    -0.06
    йте
    -0.06
     ape
    -0.06
    '];?>
    -0.06
     ){↵↵
    -0.06
    POSITIVE LOGITS
    лин
    0.07
    松
    0.07
    wu
    0.07
    概念
    0.07
     Funding
    0.06
     Searching
    0.06
    Rated
    0.06
    Vintage
    0.06
    InstantiationException
    0.06
    unding
    0.06
    Act Density 0.009%

    No Known Activations