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

    Neuronpedia

    INDEX
    Explanations

    code, translation, programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大
    0.46
    New
    0.46
    .,
    0.44
    .*
    0.44
    Tree
    0.44
    DE
    0.43
    JE
    0.43
    *
    0.43
    ._
    0.42
    Wonder
    0.42
    POSITIVE LOGITS
    también
    0.53
     மாத
    0.51
     clases
    0.49
     энерги
    0.49
    ედერ
    0.48
     ვა
    0.47
     intelectual
    0.47
    izmi
    0.47
     suport
    0.47
    積極的に
    0.47
    Act Density 0.001%

    No Known Activations