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

    Neuronpedia

    INDEX
    Explanations

    application/json content type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     type
    0.42
    类型
    0.42
    폼
    0.39
     FormData
    0.38
    ორცი
    0.38
     variedade
    0.37
    フォーム
    0.37
     variety
    0.36
     类型
    0.36
     NodeType
    0.36
    POSITIVE LOGITS
    ention
    0.37
    Opposition
    0.37
    ahanam
    0.37
     earners
    0.37
     Aa
    0.36
     aceptar
    0.36
     ଗ
    0.36
    acceptance
    0.36
     Opposition
    0.35
    icket
    0.35
    Act Density 0.002%

    No Known Activations