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

    Neuronpedia

    INDEX
    Explanations

    Robot Restaurant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mischiev
    0.45
    வே
    0.44
     ruffled
    0.44
     Chemicals
    0.43
     disfraz
    0.43
    chemicals
    0.43
     发表于
    0.42
     chemicals
    0.41
    启动
    0.41
    陡
    0.41
    POSITIVE LOGITS
     yks
    0.45
     rctx
    0.44
     vän
    0.41
     優
    0.40
     తమ
    0.39
     पहुंचकर
    0.39
     unification
    0.39
    েলি
    0.38
     sumar
    0.38
    屬於
    0.38
    Act Density 0.014%

    No Known Activations