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

    Neuronpedia

    INDEX
    Explanations

    xpath locators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portuguese
    0.41
    gester
    0.40
     жид
    0.40
    istungs
    0.40
    淍
    0.40
     travailler
    0.39
    crops
    0.39
    %";
    0.39
    醗
    0.39
    谔
    0.39
    POSITIVE LOGITS
     locator
    0.74
     xpath
    0.62
     Locator
    0.61
     XPath
    0.59
    locator
    0.58
     Indonesia
    0.56
     Malaysia
    0.55
     Jakarta
    0.54
     loc
    0.53
    xpath
    0.53
    Act Density 0.003%

    No Known Activations