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

    Neuronpedia

    INDEX
    Explanations

    requirements to include specific sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дання
    0.42
    лення
    0.39
     destiny
    0.37
    женные
    0.35
    olari
    0.35
    )}^{
    0.35
    ளுடன்
    0.35
    太平
    0.35
    谈判
    0.34
     Destiny
    0.34
    POSITIVE LOGITS
    odoc
    0.50
     DOC
    0.45
    doc
    0.44
    Doc
    0.44
     doc
    0.44
    BeforeText
    0.44
     Doc
    0.44
    DOC
    0.43
     dioxane
    0.43
    इंड
    0.42
    Act Density 0.016%

    No Known Activations